what to use in a rhetorical analysis essay

Essay Papers Writing Online

Tips and strategies for crafting a comprehensive rhetorical analysis essay.

Are you struggling to understand how to analyze and interpret rhetorical techniques in a text? Writing a rhetorical analysis essay can be a daunting task, but with the right guidance, you can master this skill and produce a compelling analysis. By delving into the strategies used by writers to persuade their audience, you can uncover the deeper meaning behind a piece of writing and develop a deeper appreciation for the art of persuasion.

In this comprehensive guide, we will walk you through the steps to writing a successful rhetorical analysis essay. From identifying the rhetorical devices used in a text to crafting a strong thesis statement, we will provide you with the tools you need to excel in this type of academic writing.

Whether you are a student looking to improve your analytical skills or a writer aiming to enhance your persuasive techniques, this guide will equip you with the knowledge and strategies to effectively analyze and critique rhetorical elements in any text.

The Basics of Rhetorical Analysis Essays

Rhetorical analysis essays are a type of academic writing where students analyze the strategies used by authors to persuade their audience. These essays typically focus on examining the appeals (ethos, logos, pathos), tone, structure, and writing style of a text to understand how the author conveys their message. To write a successful rhetorical analysis essay, students must not only analyze the text but also evaluate the effectiveness of the author’s rhetorical choices in achieving their intended purpose.

Understanding Rhetorical Techniques

Rhetorical techniques are tools used by writers and speakers to effectively communicate their ideas and persuade their audience. By understanding these techniques, you can analyze how they are used in a text or speech to strengthen the argument and appeal to the audience.

• Logos: This rhetorical technique appeals to logic and reason. It involves using facts, statistics, and logical reasoning to support an argument.
• Pathos: Pathos appeals to the emotions of the audience. It involves using storytelling, vivid language, and emotional anecdotes to connect with the audience on a deeper level.
• Ethos: Ethos focuses on establishing credibility and authority. It involves using the speaker’s expertise, moral character, and reputation to build trust with the audience.

By recognizing and analyzing these rhetorical techniques in a text, you can gain a deeper understanding of how the author or speaker is trying to persuade their audience and effectively convey their message.

Key Components of a Rhetorical Analysis

When writing a rhetorical analysis essay, there are several key components that you should consider including in your analysis:

• Rhetorical Appeals: Identify and analyze the author’s use of ethos, pathos, and logos to appeal to the audience.
• Rhetorical Strategies: Examine the different rhetorical strategies used by the author, such as repetition, imagery, and tone.
• Context: Consider the historical, cultural, and social context in which the text was written to better understand its significance.
• Audience: Analyze the target audience of the text and how the author appeals to their interests and beliefs.
• Purpose: Determine the author’s purpose for writing the text and how they use rhetoric to achieve their goals.
• Organization: Examine the structure and organization of the text to understand how the author presents their argument.
• Language: Analyze the author’s use of language, including diction, syntax, and figurative language, to convey their message.

By considering these key components in your rhetorical analysis, you can gain a deeper understanding of the text and effectively analyze the author’s use of rhetoric.

How to Start a Rhetorical Analysis

When starting a rhetorical analysis essay, it’s essential to begin by carefully reading the text you will be analyzing. Take note of the author’s purpose, audience, and message, as well as the strategies they use to convey their ideas.

Next, identify the rhetorical devices employed in the text, such as ethos, logos, and pathos. Consider how these devices contribute to the overall effectiveness of the piece and help the author achieve their goals.

It’s also crucial to analyze the structure of the text, including the organization of the arguments, the use of transitions, and the overall coherence of the writing. This will help you understand how the author builds their case and persuades the audience.

Finally, as you start writing your analysis, make sure to create a clear thesis statement that outlines the main argument of your essay. Use specific examples from the text to support your points and provide evidence for your analysis.

Structuring Your Rhetorical Analysis Essay

When structuring your rhetorical analysis essay, it is important to follow a clear and organized outline. This will help you effectively analyze the text and present your findings in a logical and coherent way. Here is a suggested structure for your essay:

Introduction: Start your essay with an introduction that provides some background information about the text you are analyzing and includes a thesis statement that states the main purpose of your analysis.

Body Paragraphs: The body of your essay should be divided into several paragraphs, each focusing on a different rhetorical strategy used in the text. Make sure to provide specific examples and evidence to support your analysis.

Conclusion: Wrap up your analysis with a conclusion that summarizes your main points and reiterates the significance of your analysis. You can also discuss the overall effectiveness of the text in achieving its intended purpose.

By following this structure, you can create a well-organized and persuasive rhetorical analysis essay that effectively analyzes the text and communicates your insights to the reader.

Developing a Strong Thesis Statement

One of the most important elements of a rhetorical analysis essay is a strong thesis statement. Your thesis statement should clearly outline the main argument you will be making in your essay. It should succinctly summarize the overall purpose and main points of your analysis. A strong thesis statement guides your analysis and helps to keep your essay focused and organized.

When developing your thesis statement, consider the rhetorical strategies used in the text you are analyzing. Think about the author’s purpose, target audience, and the techniques they use to persuade or inform. Your thesis statement should reflect your analysis of these strategies and provide a roadmap for your readers to follow as they navigate your essay.

Remember to make your thesis statement specific and debatable. Avoid vague or general statements that don’t offer a clear direction for your analysis. Your thesis should be a concise statement that presents your unique perspective on the text and sets the tone for your entire essay.

Concluding Your Rhetorical Analysis Essay

In conclusion, when wrapping up your rhetorical analysis essay, it is essential to restate your main points and thesis statement. Summarize the key rhetorical strategies used by the author and how they contributed to the overall effectiveness of the piece. Reflect on the impact of these strategies on the audience and whether they achieved the intended purpose. Additionally, provide a brief evaluation of the author’s persuasion techniques and their success in convincing the readers. Finally, leave your readers with a strong and memorable closing statement that emphasizes the significance of the analyzed text and its relevance in a broader context.

Related Post

How to master the art of writing expository essays and captivate your audience, convenient and reliable source to purchase college essays online, step-by-step guide to crafting a powerful literary analysis essay, unlock success with a comprehensive business research paper example guide, unlock your writing potential with writers college – transform your passion into profession, “unlocking the secrets of academic success – navigating the world of research papers in college”, master the art of sociological expression – elevate your writing skills in sociology.

• Affiliate Program

• UNITED STATES
• 台灣 (TAIWAN)
• TÜRKIYE (TURKEY)
• Academic Editing Services
• - Research Paper
• - Journal Manuscript
• - Dissertation
• - College & University Assignments
• Admissions Editing Services
• - Application Essay
• - Personal Statement
• - Recommendation Letter
• - Cover Letter
• - CV/Resume
• Business Editing Services
• - Business Documents
• - Report & Brochure
• - Website & Blog
• Writer Editing Services
• - Script & Screenplay
• Our Editors
• Client Reviews
• Editing & Proofreading Prices
• Wordvice Points
• Partner Discount
• Plagiarism Checker
• APA Citation Generator
• MLA Citation Generator
• Chicago Citation Generator
• Vancouver Citation Generator
• - APA Style
• - MLA Style
• - Chicago Style
• - Vancouver Style
• Writing & Editing Guide
• Academic Resources
• Admissions Resources

How to Write a Rhetorical Analysis Essay–Examples & Template

What is a Rhetorical Analysis Essay?

A rhetorical analysis essay is, as the name suggests, an analysis of someone else’s writing (or speech, or advert, or even cartoon) and how they use not only words but also rhetorical techniques to influence their audience in a certain way. A rhetorical analysis is less interested in what the author is saying and more in how they present it, what effect this has on their readers, whether they achieve their goals, and what approach they use to get there. 

Its structure is similar to that of most essays: An Introduction presents your thesis, a Body analyzes the text you have chosen, breaks it down into sections and explains how arguments have been constructed and how each part persuades, informs, or entertains the reader, and a Conclusion section sums up your evaluation. 

Note that your personal opinion on the matter is not relevant for your analysis and that you don’t state anywhere in your essay whether you agree or disagree with the stance the author takes.

In the following, we will define the key rhetorical concepts you need to write a good rhetorical analysis and give you some practical tips on where to start.

Key Rhetorical Concepts

Your goal when writing a rhetorical analysis is to think about and then carefully describe how the author has designed their text so that it has the intended effect on their audience. To do that, you need to consider a number of key rhetorical strategies: Rhetorical appeals (“Ethos”, “Logos”, and “Pathos”), context, as well as claims, supports, and warrants.

Ethos, Logos, and Pathos were introduced by Aristotle, way back in the 4th century BC, as the main ways in which language can be used to persuade an audience. They still represent the basis of any rhetorical analysis and are often referred to as the “rhetorical triangle”. 

These and other rhetorical techniques can all be combined to create the intended effect, and your job as the one analyzing a text is to break the writer’s arguments down and identify the concepts they are based on.

Rhetorical Appeals

Rhetorical appeal #1: ethos.

Ethos refers to the reputation or authority of the writer regarding the topic of their essay or speech and to how they use this to appeal to their audience. Just like we are more likely to buy a product from a brand or vendor we have confidence in than one we don’t know or have reason to distrust, Ethos-driven texts or speeches rely on the reputation of the author to persuade the reader or listener. When you analyze an essay, you should therefore look at how the writer establishes Ethos through rhetorical devices.

Does the author present themselves as an authority on their subject? If so, how? 

Do they highlight how impeccable their own behavior is to make a moral argument? 

Do they present themselves as an expert by listing their qualifications or experience to convince the reader of their opinion on something?

Rhetorical appeal #2: Pathos

The purpose of Pathos-driven rhetoric is to appeal to the reader’s emotions. A common example of pathos as a rhetorical means is adverts by charities that try to make you donate money to a “good cause”. To evoke the intended emotions in the reader, an author may use passionate language, tell personal stories, and employ vivid imagery so that the reader can imagine themselves in a certain situation and feel empathy with or anger towards others.

Rhetorical appeal #3: Logos

Logos, the “logical” appeal, uses reason to persuade. Reason and logic, supported by data, evidence, clearly defined methodology, and well-constructed arguments, are what most academic writing is based on. Emotions, those of the researcher/writer as well as those of the reader, should stay out of such academic texts, as should anyone’s reputation, beliefs, or personal opinions. 

Text and Context

To analyze a piece of writing, a speech, an advertisement, or even a satirical drawing, you need to look beyond the piece of communication and take the context in which it was created and/or published into account. 

Who is the person who wrote the text/drew the cartoon/designed the ad..? What audience are they trying to reach? Where was the piece published and what was happening there around that time? 

A political speech, for example, can be powerful even when read decades later, but the historical context surrounding it is an important aspect of the effect it was intended to have. 

Claims, Supports, and Warrants

To make any kind of argument, a writer needs to put forward specific claims, support them with data or evidence or even a moral or emotional appeal, and connect the dots logically so that the reader can follow along and agree with the points made.

The connections between statements, so-called “warrants”, follow logical reasoning but are not always clearly stated—the author simply assumes the reader understands the underlying logic, whether they present it “explicitly” or “implicitly”. Implicit warrants are commonly used in advertisements where seemingly happy people use certain products, wear certain clothes, accessories, or perfumes, or live certain lifestyles – with the connotation that, first, the product/perfume/lifestyle is what makes that person happy and, second, the reader wants to be as happy as the person in the ad. Some warrants are never clearly stated, and your job when writing a rhetorical analysis essay is therefore to identify them and bring them to light, to evaluate their validity, their effect on the reader, and the use of such means by the writer/creator. 

What are the Five Rhetorical Situations?

A “rhetorical situation” refers to the circumstance behind a text or other piece of communication that arises from a given context. It explains why a rhetorical piece was created, what its purpose is, and how it was constructed to achieve its aims.

Rhetorical situations can be classified into the following five categories:

Asking such questions when you analyze a text will help you identify all the aspects that play a role in the effect it has on its audience, and will allow you to evaluate whether it achieved its aims or where it may have failed to do so.

Rhetorical Analysis Essay Outline

Analyzing someone else’s work can seem like a big task, but as with every assignment or writing endeavor, you can break it down into smaller, well-defined steps that give you a practical structure to follow. 

To give you an example of how the different parts of your text may look when it’s finished, we will provide you with some excerpts from this rhetorical analysis essay example (which even includes helpful comments) published on the Online Writing Lab website of Excelsior University in Albany, NY. The text that this essay analyzes is this article on why one should or shouldn’t buy an Ipad. If you want more examples so that you can build your own rhetorical analysis template, have a look at this essay on Nabokov’s Lolita and the one provided here about the “Shitty First Drafts” chapter of Anne Lamott’s writing instruction book “Bird by Bird”.

Analyzing the Text

When writing a rhetorical analysis, you don’t choose the concepts or key points you think are relevant or want to address. Rather, you carefully read the text several times asking yourself questions like those listed in the last section on rhetorical situations to identify how the text “works” and how it was written to achieve that effect.

Start with focusing on the author : What do you think was their purpose for writing the text? Do they make one principal claim and then elaborate on that? Or do they discuss different topics? 

Then look at what audience they are talking to: Do they want to make a group of people take some action? Vote for someone? Donate money to a good cause? Who are these people? Is the text reaching this specific audience? Why or why not?

What tone is the author using to address their audience? Are they trying to evoke sympathy? Stir up anger? Are they writing from a personal perspective? Are they painting themselves as an authority on the topic? Are they using academic or informal language?

How does the author support their claims ? What kind of evidence are they presenting? Are they providing explicit or implicit warrants? Are these warrants valid or problematic? Is the provided evidence convincing?  

Asking yourself such questions will help you identify what rhetorical devices a text uses and how well they are put together to achieve a certain aim. Remember, your own opinion and whether you agree with the author are not the point of a rhetorical analysis essay – your task is simply to take the text apart and evaluate it.

If you are still confused about how to write a rhetorical analysis essay, just follow the steps outlined below to write the different parts of your rhetorical analysis: As every other essay, it consists of an Introduction , a Body (the actual analysis), and a Conclusion .

Rhetorical Analysis Introduction

The Introduction section briefly presents the topic of the essay you are analyzing, the author, their main claims, a short summary of the work by you, and your thesis statement . 

Tell the reader what the text you are going to analyze represents (e.g., historically) or why it is relevant (e.g., because it has become some kind of reference for how something is done). Describe what the author claims, asserts, or implies and what techniques they use to make their argument and persuade their audience. Finish off with your thesis statement that prepares the reader for what you are going to present in the next section – do you think that the author’s assumptions/claims/arguments were presented in a logical/appealing/powerful way and reached their audience as intended?

Have a look at an excerpt from the sample essay linked above to see what a rhetorical analysis introduction can look like. See how it introduces the author and article , the context in which it originally appeared , the main claims the author makes , and how this first paragraph ends in a clear thesis statement that the essay will then elaborate on in the following Body section:

Cory Doctorow ’s article on BoingBoing is an older review of the iPad , one of Apple’s most famous products. At the time of this article, however, the iPad was simply the latest Apple product to hit the market and was not yet so popular. Doctorow’s entire career has been entrenched in and around technology. He got his start as a CD-ROM programmer and is now a successful blogger and author. He is currently the co-editor of the BoingBoing blog on which this article was posted. One of his main points in this article comes from Doctorow’s passionate advocacy of free digital media sharing. He argues that the iPad is just another way for established technology companies to control our technological freedom and creativity . In “ Why I Won’t Buy an iPad (and Think You Shouldn’t, Either) ” published on Boing Boing in April of 2010, Cory Doctorow successfully uses his experience with technology, facts about the company Apple, and appeals to consumer needs to convince potential iPad buyers that Apple and its products, specifically the iPad, limit the digital rights of those who use them by controlling and mainstreaming the content that can be used and created on the device . 

Doing the Rhetorical Analysis

The main part of your analysis is the Body , where you dissect the text in detail. Explain what methods the author uses to inform, entertain, and/or persuade the audience. Use Aristotle’s rhetorical triangle and the other key concepts we introduced above. Use quotations from the essay to demonstrate what you mean. Work out why the writer used a certain approach and evaluate (and again, demonstrate using the text itself) how successful they were. Evaluate the effect of each rhetorical technique you identify on the audience and judge whether the effect is in line with the author’s intentions.

To make it easy for the reader to follow your thought process, divide this part of your essay into paragraphs that each focus on one strategy or one concept , and make sure they are all necessary and contribute to the development of your argument(s).

One paragraph of this section of your essay could, for example, look like this:

One example of Doctorow’s position is his comparison of Apple’s iStore to Wal-Mart. This is an appeal to the consumer’s logic—or an appeal to logos. Doctorow wants the reader to take his comparison and consider how an all-powerful corporation like the iStore will affect them. An iPad will only allow for apps and programs purchased through the iStore to be run on it; therefore, a customer must not only purchase an iPad but also any programs he or she wishes to use. Customers cannot create their own programs or modify the hardware in any way. 

As you can see, the author of this sample essay identifies and then explains to the reader how Doctorow uses the concept of Logos to appeal to his readers – not just by pointing out that he does it but by dissecting how it is done.

Rhetorical Analysis Conclusion

The conclusion section of your analysis should restate your main arguments and emphasize once more whether you think the author achieved their goal. Note that this is not the place to introduce new information—only rely on the points you have discussed in the body of your essay. End with a statement that sums up the impact the text has on its audience and maybe society as a whole:

Overall, Doctorow makes a good argument about why there are potentially many better things to drop a great deal of money on instead of the iPad. He gives some valuable information and facts that consumers should take into consideration before going out to purchase the new device. He clearly uses rhetorical tools to help make his case, and, overall, he is effective as a writer, even if, ultimately, he was ineffective in convincing the world not to buy an iPad . 

Frequently Asked Questions about Rhetorical Analysis Essays 

What is a rhetorical analysis essay.

A rhetorical analysis dissects a text or another piece of communication to work out and explain how it impacts its audience, how successfully it achieves its aims, and what rhetorical devices it uses to do that. 

While argumentative essays usually take a stance on a certain topic and argue for it, a rhetorical analysis identifies how someone else constructs their arguments and supports their claims.

What is the correct rhetorical analysis essay format?

Like most other essays, a rhetorical analysis contains an Introduction that presents the thesis statement, a Body that analyzes the piece of communication, explains how arguments have been constructed, and illustrates how each part persuades, informs, or entertains the reader, and a Conclusion section that summarizes the results of the analysis. 

What is the “rhetorical triangle”?

The rhetorical triangle was introduced by Aristotle as the main ways in which language can be used to persuade an audience: Logos appeals to the audience’s reason, Ethos to the writer’s status or authority, and Pathos to the reader’s emotions. Logos, Ethos, and Pathos can all be combined to create the intended effect, and your job as the one analyzing a text is to break the writer’s arguments down and identify what specific concepts each is based on.

Let Wordvice help you write a flawless rhetorical analysis essay! 

Whether you have to write a rhetorical analysis essay as an assignment or whether it is part of an application, our professional proofreading services feature professional editors are trained subject experts that make sure your text is in line with the required format, as well as help you improve the flow and expression of your writing. Let them be your second pair of eyes so that after receiving paper editing services or essay editing services from Wordvice, you can submit your manuscript or apply to the school of your dreams with confidence.

And check out our editing services for writers (including blog editing , script editing , and book editing ) to correct your important personal or business-related work.

• Features for Creative Writers
• Features for Work
• Features for Higher Education
• Features for Teachers
• Features for Non-Native Speakers
• Learn Blog Grammar Guide Community Events FAQ
• Grammar Guide

What Is a Rhetorical Analysis and How to Write a Great One

Helly Douglas

Do you have to write a rhetorical analysis essay? Fear not! We’re here to explain exactly what rhetorical analysis means, how you should structure your essay, and give you some essential “dos and don’ts.”

What is a Rhetorical Analysis Essay?

How do you write a rhetorical analysis, what are the three rhetorical strategies, what are the five rhetorical situations, how to plan a rhetorical analysis essay, creating a rhetorical analysis essay, examples of great rhetorical analysis essays, final thoughts.

A rhetorical analysis essay studies how writers and speakers have used words to influence their audience. Think less about the words the author has used and more about the techniques they employ, their goals, and the effect this has on the audience.

In your analysis essay, you break a piece of text (including cartoons, adverts, and speeches) into sections and explain how each part works to persuade, inform, or entertain. You’ll explore the effectiveness of the techniques used, how the argument has been constructed, and give examples from the text.

A strong rhetorical analysis evaluates a text rather than just describes the techniques used. You don’t include whether you personally agree or disagree with the argument.

Structure a rhetorical analysis in the same way as most other types of academic essays . You’ll have an introduction to present your thesis, a main body where you analyze the text, which then leads to a conclusion.

Think about how the writer (also known as a rhetor) considers the situation that frames their communication:

• Topic: the overall purpose of the rhetoric
• Audience: this includes primary, secondary, and tertiary audiences
• Purpose: there are often more than one to consider
• Context and culture: the wider situation within which the rhetoric is placed

Back in the 4th century BC, Aristotle was talking about how language can be used as a means of persuasion. He described three principal forms —Ethos, Logos, and Pathos—often referred to as the Rhetorical Triangle . These persuasive techniques are still used today.

Rhetorical Strategy 1: Ethos

Are you more likely to buy a car from an established company that’s been an important part of your community for 50 years, or someone new who just started their business?

Reputation matters. Ethos explores how the character, disposition, and fundamental values of the author create appeal, along with their expertise and knowledge in the subject area.

Aristotle breaks ethos down into three further categories:

• Phronesis: skills and practical wisdom
• Arete: virtue
• Eunoia: goodwill towards the audience

Ethos-driven speeches and text rely on the reputation of the author. In your analysis, you can look at how the writer establishes ethos through both direct and indirect means.

Rhetorical Strategy 2: Pathos

Pathos-driven rhetoric hooks into our emotions. You’ll often see it used in advertisements, particularly by charities wanting you to donate money towards an appeal.

Common use of pathos includes:

• Vivid description so the reader can imagine themselves in the situation
• Personal stories to create feelings of empathy
• Emotional vocabulary that evokes a response

By using pathos to make the audience feel a particular emotion, the author can persuade them that the argument they’re making is compelling.

Rhetorical Strategy 3: Logos

Logos uses logic or reason. It’s commonly used in academic writing when arguments are created using evidence and reasoning rather than an emotional response. It’s constructed in a step-by-step approach that builds methodically to create a powerful effect upon the reader.

Rhetoric can use any one of these three techniques, but effective arguments often appeal to all three elements.

The rhetorical situation explains the circumstances behind and around a piece of rhetoric. It helps you think about why a text exists, its purpose, and how it’s carried out.

The rhetorical situations are:

• 1) Purpose: Why is this being written? (It could be trying to inform, persuade, instruct, or entertain.)
• 2) Audience: Which groups or individuals will read and take action (or have done so in the past)?
• 3) Genre: What type of writing is this?
• 4) Stance: What is the tone of the text? What position are they taking?
• 5) Media/Visuals: What means of communication are used?

Understanding and analyzing the rhetorical situation is essential for building a strong essay. Also think about any rhetoric restraints on the text, such as beliefs, attitudes, and traditions that could affect the author's decisions.

Before leaping into your essay, it’s worth taking time to explore the text at a deeper level and considering the rhetorical situations we looked at before. Throw away your assumptions and use these simple questions to help you unpick how and why the text is having an effect on the audience.

1: What is the Rhetorical Situation?

• Why is there a need or opportunity for persuasion?
• How do words and references help you identify the time and location?
• What are the rhetoric restraints?
• What historical occasions would lead to this text being created?

2: Who is the Author?

• How do they position themselves as an expert worth listening to?
• What is their ethos?
• Do they have a reputation that gives them authority?
• What is their intention?
• What values or customs do they have?

3: Who is it Written For?

• Who is the intended audience?
• How is this appealing to this particular audience?
• Who are the possible secondary and tertiary audiences?

4: What is the Central Idea?

• Can you summarize the key point of this rhetoric?
• What arguments are used?
• How has it developed a line of reasoning?

5: How is it Structured?

• What structure is used?
• How is the content arranged within the structure?

6: What Form is Used?

• Does this follow a specific literary genre?
• What type of style and tone is used, and why is this?
• Does the form used complement the content?
• What effect could this form have on the audience?

7: Is the Rhetoric Effective?

• Does the content fulfil the author’s intentions?
• Does the message effectively fit the audience, location, and time period?

Once you’ve fully explored the text, you’ll have a better understanding of the impact it’s having on the audience and feel more confident about writing your essay outline.

A great essay starts with an interesting topic. Choose carefully so you’re personally invested in the subject and familiar with it rather than just following trending topics. There are lots of great ideas on this blog post by My Perfect Words if you need some inspiration. Take some time to do background research to ensure your topic offers good analysis opportunities.

Remember to check the information given to you by your professor so you follow their preferred style guidelines. This outline example gives you a general idea of a format to follow, but there will likely be specific requests about layout and content in your course handbook. It’s always worth asking your institution if you’re unsure.

Make notes for each section of your essay before you write. This makes it easy for you to write a well-structured text that flows naturally to a conclusion. You will develop each note into a paragraph. Look at this example by College Essay for useful ideas about the structure.

1: Introduction

This is a short, informative section that shows you understand the purpose of the text. It tempts the reader to find out more by mentioning what will come in the main body of your essay.

• Name the author of the text and the title of their work followed by the date in parentheses
• Use a verb to describe what the author does, e.g. “implies,” “asserts,” or “claims”
• Briefly summarize the text in your own words
• Mention the persuasive techniques used by the rhetor and its effect

Create a thesis statement to come at the end of your introduction.

After your introduction, move on to your critical analysis. This is the principal part of your essay.

• Explain the methods used by the author to inform, entertain, and/or persuade the audience using Aristotle's rhetorical triangle
• Use quotations to prove the statements you make
• Explain why the writer used this approach and how successful it is
• Consider how it makes the audience feel and react

Make each strategy a new paragraph rather than cramming them together, and always use proper citations. Check back to your course handbook if you’re unsure which citation style is preferred.

3: Conclusion

Your conclusion should summarize the points you’ve made in the main body of your essay. While you will draw the points together, this is not the place to introduce new information you’ve not previously mentioned.

Use your last sentence to share a powerful concluding statement that talks about the impact the text has on the audience(s) and wider society. How have its strategies helped to shape history?

Before You Submit

Poor spelling and grammatical errors ruin a great essay. Use ProWritingAid to check through your finished essay before you submit. It will pick up all the minor errors you’ve missed and help you give your essay a final polish. Look at this useful ProWritingAid webinar for further ideas to help you significantly improve your essays. Sign up for a free trial today and start editing your essays!

You’ll find countless examples of rhetorical analysis online, but they range widely in quality. Your institution may have example essays they can share with you to show you exactly what they’re looking for.

The following links should give you a good starting point if you’re looking for ideas:

Pearson Canada has a range of good examples. Look at how embedded quotations are used to prove the points being made. The end questions help you unpick how successful each essay is.

Excelsior College has an excellent sample essay complete with useful comments highlighting the techniques used.

Brighton Online has a selection of interesting essays to look at. In this specific example, consider how wider reading has deepened the exploration of the text.

Writing a rhetorical analysis essay can seem daunting, but spending significant time deeply analyzing the text before you write will make it far more achievable and result in a better-quality essay overall.

It can take some time to write a good essay. Aim to complete it well before the deadline so you don’t feel rushed. Use ProWritingAid’s comprehensive checks to find any errors and make changes to improve readability. Then you’ll be ready to submit your finished essay, knowing it’s as good as you can possibly make it.

Try ProWritingAid's Editor for Yourself

Be confident about grammar

Check every email, essay, or story for grammar mistakes. Fix them before you press send.

Helly Douglas is a UK writer and teacher, specialising in education, children, and parenting. She loves making the complex seem simple through blogs, articles, and curriculum content. You can check out her work at hellydouglas.com or connect on Twitter @hellydouglas. When she’s not writing, you will find her in a classroom, being a mum or battling against the wilderness of her garden—the garden is winning!

Get started with ProWritingAid

Drop us a line or let's stay in touch via :

Reference management. Clean and simple.

How to write a rhetorical analysis

What is a rhetorical analysis?

What are the key concepts of a rhetorical analysis, rhetorical situation, claims, supports, and warrants.

• Step 1: Plan and prepare
• Step 2: Write your introduction
• Step 3: Write the body
• Step 4: Write your conclusion

Frequently Asked Questions about rhetorical analysis

Related articles.

Rhetoric is the art of persuasion and aims to study writers’ or speakers' techniques to inform, persuade, or motivate their audience. Thus, a rhetorical analysis aims to explore the goals and motivations of an author, the techniques they’ve used to reach their audience, and how successful these techniques were.

This will generally involve analyzing a specific text and considering the following aspects to connect the rhetorical situation to the text:

• Does the author successfully support the thesis or claims made in the text? Here, you’ll analyze whether the author holds to their argument consistently throughout the text or whether they wander off-topic at some point.
• Does the author use evidence effectively considering the text’s intended audience? Here, you’ll consider the evidence used by the author to support their claims and whether the evidence resonates with the intended audience.
• What rhetorical strategies the author uses to achieve their goals. Here, you’ll consider the word choices by the author and whether these word choices align with their agenda for the text.
• The tone of the piece. Here, you’ll consider the tone used by the author in writing the piece by looking at specific words and aspects that set the tone.
• Whether the author is objective or trying to convince the audience of a particular viewpoint. When it comes to objectivity, you’ll consider whether the author is objective or holds a particular viewpoint they want to convince the audience of. If they are, you’ll also consider whether their persuasion interferes with how the text is read and understood.
• Does the author correctly identify the intended audience? It’s important to consider whether the author correctly writes the text for the intended audience and what assumptions the author makes about the audience.
• Does the text make sense? Here, you’ll consider whether the author effectively reasons, based on the evidence, to arrive at the text’s conclusion.
• Does the author try to appeal to the audience’s emotions? You’ll need to consider whether the author uses any words, ideas, or techniques to appeal to the audience’s emotions.
• Can the author be believed? Finally, you’ll consider whether the audience will accept the arguments and ideas of the author and why.

Summing up, unlike summaries that focus on what an author said, a rhetorical analysis focuses on how it’s said, and it doesn’t rely on an analysis of whether the author was right or wrong but rather how they made their case to arrive at their conclusions.

Although rhetorical analysis is most used by academics as part of scholarly work, it can be used to analyze any text including speeches, novels, television shows or films, advertisements, or cartoons.

Now that we’ve seen what rhetorical analysis is, let’s consider some of its key concepts .

Any rhetorical analysis starts with the rhetorical situation which identifies the relationships between the different elements of the text. These elements include the audience, author or writer, the author’s purpose, the delivery method or medium, and the content:

• Audience: The audience is simply the readers of a specific piece of text or content or printed material. For speeches or other mediums like film and video, the audience would be the listeners or viewers. Depending on the specific piece of text or the author’s perception, the audience might be real, imagined, or invoked. With a real audience, the author writes to the people actually reading or listening to the content while, for an imaginary audience, the author writes to an audience they imagine would read the content. Similarly, for an invoked audience, the author writes explicitly to a specific audience.
• Author or writer: The author or writer, also commonly referred to as the rhetor in the context of rhetorical analysis, is the person or the group of persons who authored the text or content.
• The author’s purpose: The author’s purpose is the author’s reason for communicating to the audience. In other words, the author’s purpose encompasses what the author expects or intends to achieve with the text or content.
• Alphabetic text includes essays, editorials, articles, speeches, and other written pieces.
• Imaging includes website and magazine advertisements, TV commercials, and the like.
• Audio includes speeches, website advertisements, radio or tv commercials, or podcasts.
• Context: The context of the text or content considers the time, place, and circumstances surrounding the delivery of the text to its audience. With respect to context, it might often also be helpful to analyze the text in a different context to determine its impact on a different audience and in different circumstances.

An author will use claims, supports, and warrants to build the case around their argument, irrespective of whether the argument is logical and clearly defined or needs to be inferred by the audience:

• Claim: The claim is the main idea or opinion of an argument that the author must prove to the intended audience. In other words, the claim is the fact or facts the author wants to convince the audience of. Claims are usually explicitly stated but can, depending on the specific piece of content or text, be implied from the content. Although these claims could be anything and an argument may be based on a single or several claims, the key is that these claims should be debatable.
• Support: The supports are used by the author to back up the claims they make in their argument. These supports can include anything from fact-based, objective evidence to subjective emotional appeals and personal experiences used by the author to convince the audience of a specific claim. Either way, the stronger and more reliable the supports, the more likely the audience will be to accept the claim.
• Warrant: The warrants are the logic and assumptions that connect the supports to the claims. In other words, they’re the assumptions that make the initial claim possible. The warrant is often unstated, and the author assumes that the audience will be able to understand the connection between the claims and supports. In turn, this is based on the author’s assumption that they share a set of values and beliefs with the audience that will make them understand the connection mentioned above. Conversely, if the audience doesn’t share these beliefs and values with the author, the argument will not be that effective.

Appeals are used by authors to convince their audience and, as such, are an integral part of the rhetoric and are often referred to as the rhetorical triangle. As a result, an author may combine all three appeals to convince their audience:

• Ethos: Ethos represents the authority or credibility of the author. To be successful, the author needs to convince the audience of their authority or credibility through the language and delivery techniques they use. This will, for example, be the case where an author writing on a technical subject positions themselves as an expert or authority by referring to their qualifications or experience.
• Logos: Logos refers to the reasoned argument the author uses to persuade their audience. In other words, it refers to the reasons or evidence the author proffers in substantiation of their claims and can include facts, statistics, and other forms of evidence. For this reason, logos is also the dominant approach in academic writing where authors present and build up arguments using reasoning and evidence.
• Pathos: Through pathos, also referred to as the pathetic appeal, the author attempts to evoke the audience’s emotions through the use of, for instance, passionate language, vivid imagery, anger, sympathy, or any other emotional response.

To write a rhetorical analysis, you need to follow the steps below:

With a rhetorical analysis, you don’t choose concepts in advance and apply them to a specific text or piece of content. Rather, you’ll have to analyze the text to identify the separate components and plan and prepare your analysis accordingly.

Here, it might be helpful to use the SOAPSTone technique to identify the components of the work. SOAPSTone is a common acronym in analysis and represents the:

• Speaker . Here, you’ll identify the author or the narrator delivering the content to the audience.
• Occasion . With the occasion, you’ll identify when and where the story takes place and what the surrounding context is.
• Audience . Here, you’ll identify who the audience or intended audience is.
• Purpose . With the purpose, you’ll need to identify the reason behind the text or what the author wants to achieve with their writing.
• Subject . You’ll also need to identify the subject matter or topic of the text.
• Tone . The tone identifies the author’s feelings towards the subject matter or topic.

Apart from gathering the information and analyzing the components mentioned above, you’ll also need to examine the appeals the author uses in writing the text and attempting to persuade the audience of their argument. Moreover, you’ll need to identify elements like word choice, word order, repetition, analogies, and imagery the writer uses to get a reaction from the audience.

Once you’ve gathered the information and examined the appeals and strategies used by the author as mentioned above, you’ll need to answer some questions relating to the information you’ve collected from the text. The answers to these questions will help you determine the reasons for the choices the author made and how well these choices support the overall argument.

Here, some of the questions you’ll ask include:

• What was the author’s intention?
• Who was the intended audience?
• What is the author’s argument?
• What strategies does the author use to build their argument and why do they use those strategies?
• What appeals the author uses to convince and persuade the audience?
• What effect the text has on the audience?

Keep in mind that these are just some of the questions you’ll ask, and depending on the specific text, there might be others.

Once you’ve done your preparation, you can start writing the rhetorical analysis. It will start off with an introduction which is a clear and concise paragraph that shows you understand the purpose of the text and gives more information about the author and the relevance of the text.

The introduction also summarizes the text and the main ideas you’ll discuss in your analysis. Most importantly, however, is your thesis statement . This statement should be one sentence at the end of the introduction that summarizes your argument and tempts your audience to read on and find out more about it.

After your introduction, you can proceed with the body of your analysis. Here, you’ll write at least three paragraphs that explain the strategies and techniques used by the author to convince and persuade the audience, the reasons why the writer used this approach, and why it’s either successful or unsuccessful.

You can structure the body of your analysis in several ways. For example, you can deal with every strategy the author uses in a new paragraph, but you can also structure the body around the specific appeals the author used or chronologically.

No matter how you structure the body and your paragraphs, it’s important to remember that you support each one of your arguments with facts, data, examples, or quotes and that, at the end of every paragraph, you tie the topic back to your original thesis.

Finally, you’ll write the conclusion of your rhetorical analysis. Here, you’ll repeat your thesis statement and summarize the points you’ve made in the body of your analysis. Ultimately, the goal of the conclusion is to pull the points of your analysis together so you should be careful to not raise any new issues in your conclusion.

After you’ve finished your conclusion, you’ll end your analysis with a powerful concluding statement of why your argument matters and an invitation to conduct more research if needed.

A rhetorical analysis aims to explore the goals and motivations of an author, the techniques they’ve used to reach their audience, and how successful these techniques were. Although rhetorical analysis is most used by academics as part of scholarly work, it can be used to analyze any text including speeches, novels, television shows or films, advertisements, or cartoons.

The steps to write a rhetorical analysis include:

Your rhetorical analysis introduction is a clear and concise paragraph that shows you understand the purpose of the text and gives more information about the author and the relevance of the text. The introduction also summarizes the text and the main ideas you’ll discuss in your analysis.

Ethos represents the authority or credibility of the author. To be successful, the author needs to convince the audience of their authority or credibility through the language and delivery techniques they use. This will, for example, be the case where an author writing on a technical subject positions themselves as an expert or authority by referring to their qualifications or experience.

Appeals are used by authors to convince their audience and, as such, are an integral part of the rhetoric and are often referred to as the rhetorical triangle. The 3 types of appeals are ethos, logos, and pathos.

• Link to facebook
• Link to linkedin
• Link to twitter
• Link to youtube
• Writing Tips

How to Write a Rhetorical Analysis Essay

3-minute read

• 22nd August 2023

A rhetorical analysis essay is a type of academic writing that analyzes how authors use language, persuasion techniques , and other rhetorical strategies to communicate with their audience. In this post, we’ll review how to write a rhetorical analysis essay, including:

• Understanding the assignment guidelines
• Introducing your essay topic
• Examining the rhetorical strategies
• Summarizing your main points

Keep reading for a step-by-step guide to rhetorical analysis.

What Is a Rhetorical Strategy?

A rhetorical strategy is a deliberate approach or technique a writer uses to convey a message and/or persuade the audience. A rhetorical strategy typically involves using language, sentence structure, and tone/style to influence the audience to think a certain way or understand a specific point of view. Rhetorical strategies are especially common in advertisements, speeches, and political writing, but you can also find them in many other types of literature.

1.   Understanding the Assignment Guidelines

Before you begin your rhetorical analysis essay, make sure you understand the assignment and guidelines. Typically, when writing a rhetorical analysis, you should approach the text objectively, focusing on the techniques the author uses rather than expressing your own opinions about the topic or summarizing the content. Thus, it’s essential to discuss the rhetorical methods used and then back up your analysis with evidence and quotations from the text.

2.   Introducing Your Essay Topic

Introduce your essay by providing some context about the text you’re analyzing. Give a brief overview of the author, intended audience, and purpose of the writing. You should also clearly state your thesis , which is your main point or argument about how and why the author uses rhetorical strategies. Try to avoid going into detail on any points or diving into specific examples – the introduction should be concise, and you’ll be providing a much more in-depth analysis later in the text.

3.   Examining the Rhetorical Strategies

In the body paragraphs, analyze the rhetorical strategies the author uses. Here are some common rhetorical strategies to include in your discussion:

●  Ethos : Establishing trust between the writer and the audience by appealing to credibility and ethics

●  Pathos : Appealing to the audience’s emotions and values

●  Logos : Employing logic, reason, and evidence to appeal to the reader

Find this useful?

Subscribe to our newsletter and get writing tips from our editors straight to your inbox.

●  Diction : Deliberately choosing specific language and vocabulary

●  Syntax : Structuring and arranging sentences in certain ways

●  Tone : Conveying attitude or mood in certain ways

●  Literary Devices : Using metaphors, similes, analogies , repetition, etc.

Keep in mind that for a rhetorical analysis essay, you’re not usually required to find examples of all of the above rhetorical strategies. But for each one you do analyze, consider how it contributes to the author’s purpose, how it influences the audience, and what emotions or thoughts it could evoke in the reader.

4.   Summarizing Your Main Points

In your conclusion , sum up the main points of your analysis and restate your thesis. Without introducing any new points (such as topics or ideas you haven’t already covered in the main body of your essay), summarize the overall impact that the author’s rhetorical strategies likely had on their intended audience.

Expert Proofreading Services

Ensure that your rhetorical analysis essay stands out by having our expert team proofread it. Send in your free sample of 500 words or less and see for yourself the difference in your work!

Share this article:

Post A New Comment

Got content that needs a quick turnaround? Let us polish your work. Explore our editorial business services.

9-minute read

How to Use Infographics to Boost Your Presentation

Is your content getting noticed? Capturing and maintaining an audience’s attention is a challenge when...

8-minute read

Why Interactive PDFs Are Better for Engagement

Are you looking to enhance engagement and captivate your audience through your professional documents? Interactive...

7-minute read

Seven Key Strategies for Voice Search Optimization

Voice search optimization is rapidly shaping the digital landscape, requiring content professionals to adapt their...

4-minute read

Five Creative Ways to Showcase Your Digital Portfolio

Are you a creative freelancer looking to make a lasting impression on potential clients or...

How to Ace Slack Messaging for Contractors and Freelancers

Effective professional communication is an important skill for contractors and freelancers navigating remote work environments....

How to Insert a Text Box in a Google Doc

Google Docs is a powerful collaborative tool, and mastering its features can significantly enhance your...

Make sure your writing is the best it can be with our expert English proofreading and editing.

How to Write a Rhetorical Analysis: Full Guide

Have you ever been completely fascinated by a speech or ad, wondering how it managed to convince you so effectively? From powerful political speeches to catchy commercials, persuasion is all around us, shaping our thoughts and choices every day.

In this guide, we'll explain all about a rhetorical analysis essay. We'll break down the clever tricks writers and speakers use to win over their audience, like how they choose their words carefully and play with our emotions. This article will give you the tools you need to understand and analyze texts more deeply. So, let’s jump right in and start by understanding the nature of this assignment first.

What is a Rhetorical Analysis Essay

A rhetorical analysis essay is a type of essay where you examine how authors or speakers use words, phrases, and other techniques to influence or persuade their audience. This type of essay focuses on analyzing the strategies used by the writer or speaker to achieve their purpose, whether it's to inform, persuade, entertain, or provoke.

You'll dissect the text or speech into its components, looking at how each part contributes to the overall message. This might involve examining the introduction, thesis statement, body paragraphs, evidence, and conclusion.

Once you've identified the strategies used, you'll assess their effectiveness in achieving the author's or speaker's purpose. This involves considering the intended audience, context, and the impact of the communication.

As per our essay writing service , some common topics for rhetorical analysis include analyzing speeches by influential leaders, dissecting political advertisements, or examining the rhetoric used in literary works.

Do You Want to Ease Your Academic Burden?

Order a rhetorical analysis essay from our expert writers today and experience the power of top-notch academic writing.

Rhetorical Analysis Topic Ideas

Now that we've grasped the essence of a rhetorical analysis essay let's explore some potential topics you might consider for your own analysis. Here are 15 specific ideas to get you started:

• The Use of Metaphors in Barack Obama's 'Yes We Can' Speech
• Visual Rhetoric in Dove's 'Real Beauty' Advertising Campaign
• The Role of Irony in Jonathan Swift's 'A Modest Proposal'
• The Manipulation of Emotions in Coca-Cola's 'Share a Coke' Campaign
• The Repetition Technique in Winston Churchill's 'We Shall Fight on the Beaches' Speech
• The Argument Structure in Michelle Obama's Speech on Education
• The Use of Imagery in Edgar Allan Poe's 'The Raven'
• Gender Stereotypes in Old Spice's 'The Man Your Man Could Smell Like' Ad
• Satirical Elements in George Orwell's 'Animal Farm'
• The Influence of Tone in Greta Thunberg's Climate Change Speeches
• Political Symbolism in Banksy's Street Art
• Humor as Persuasion in Ellen DeGeneres' Stand-Up Comedy
• The Power of Silence in Emma Watson's UN Speech on Gender Equality
• Ethical Appeals in ASPCA's Animal Rights Advertisements
• The Cultural References in Super Bowl Commercials: A Case Study

How to Write a Rhetorical Analysis

Understanding how to start a rhetorical analysis essay involves dissecting a piece of communication to learn how it works and what effect it aims to achieve. This analytical process typically includes five paragraphs and three main parts: an introduction, three body paragraphs, and a conclusion. Below, our analytical essay writing service will explain each in more detail

Major Rhetorical Elements

Before heading towards the analysis process, it's essential to grasp some key rhetorical concepts that will help guide your examination of the text or speech. These concepts provide a framework for understanding how authors and speakers use language to persuade and influence their audience.

Ethos, pathos logos in rhetorical analysis form the foundation of persuasive communication and are often intertwined in rhetorical strategies. Ethos refers to the credibility or authority of the speaker or author. Pathos involves appealing to the audience's emotions, while logos appeals to reason and logic.

There are also other rhetorical devices that are specific techniques or patterns of language used to convey meaning or evoke particular responses. Examples include metaphor, simile, imagery, irony, repetition, and hyperbole. Recognizing and analyzing these devices can provide insight into the author's intended message and its impact on the audience.

Tone and mood also play crucial roles in shaping the audience's perception and response to the communication. Tone refers to the author's attitude toward the subject matter, while mood describes the emotional atmosphere created by the text.

Whether you ask us - write my essay , or tackle the task yourself, familiarizing yourself with these concepts will help you analyze the text and persuade the audience more effectively.

Understanding Rhetorical Appeals

First off, what is ethos in rhetorical analysis? Well, it revolves around establishing the credibility and authority of the speaker or author. This appeal seeks to convince the audience that the communicator is trustworthy, knowledgeable, and reliable. Ethos in rhetorical analysis can be built through various means, including:

• Professional Credentials : Demonstrating expertise in the subject matter through relevant qualifications or experience.
• Personal Character : Highlighting traits such as honesty, integrity, and sincerity to engender trust and respect.
• Association : Aligning oneself with respected individuals, institutions, or causes to enhance credibility by association.

For instance, in a health-related speech, a doctor might leverage their medical expertise and professional experience (credentials) to establish ethos. Similarly, a celebrity endorsing a product is using their fame and reputation (association) to persuade consumers.

Now, let's understand what is pathos in rhetorical analysis. Pathos involves appealing to the audience's emotions, aiming to evoke feelings such as empathy, sympathy, joy, anger, or fear. This emotional connection can be a powerful tool for persuasion, as it resonates with the audience on a personal level. Strategies for employing pathos in rhetorical analysis include:

• Vivid Imagery : Painting a vivid picture or narrative that elicits strong emotional responses from the audience.
• Anecdotes : Sharing personal stories or anecdotes that evoke empathy or sympathy and make the message more relatable.
• Language Choice : Using emotive language, sensory details, and rhetorical devices to evoke specific emotional reactions.

For example, in a charity advertisement for children in need, images of impoverished and suffering children coupled with heart-wrenching stories (anecdotes) are used to evoke feelings of compassion and a desire to help.

Lastly, what is logos in rhetorical analysis, you may ask. It appeals to reason and logic, aiming to persuade the audience through rational argumentation and evidence. This appeal relies on facts, statistics, logical reasoning, and sound arguments to convince the audience of the validity of the message. Strategies for employing logos in rhetorical analysis include:

• Factual Evidence : Providing empirical data, research findings, or expert opinions to support the argument.
• Logical Reasoning : Presenting a well-structured argument with clear premises and conclusions that logically follow one another.
• Counterarguments : Addressing potential counterarguments and refuting them with logical reasoning and evidence.

For instance, in a persuasive essay advocating for environmental conservation, the author might present scientific data on climate change (factual evidence) and use logical reasoning to explain the consequences of inaction.

Text and Context

Text analysis involves closely examining the language, structure, and rhetorical devices employed within the communication. This includes identifying key themes, rhetorical appeals, persuasive strategies, and stylistic elements used by the author or speaker to convey their message.

For example, in a political speech advocating for healthcare reform, text analysis might involve identifying the use of rhetorical appeals such as ethos (e.g., highlighting the speaker's experience in healthcare policy), pathos (e.g., sharing anecdotes of individuals struggling with medical costs), and logos (e.g., presenting statistics on healthcare affordability).

Contextual analysis involves considering the broader social, cultural, and historical factors that shape communication and influence its reception. This includes examining the audience demographics, the political and cultural climate, the historical events surrounding the communication, and any relevant societal norms or values.

For instance, when analyzing a historical speech advocating for civil rights, contextual research paper writers might involve considering the social and political context of the time, including prevailing attitudes towards race, ongoing civil rights movements, and recent legislative developments.

Claims, Supports, and Warrants

A claim is a statement or assertion that the author or speaker is advocating for or seeking to prove. Claims can take various forms, including factual claims (assertions of fact), value claims (judgments about what is good or bad), and policy claims (proposals for action). For example, in an argumentative essay about the importance of exercise, the claim might be that regular physical activity is essential for maintaining good health.

Supports are the evidence, reasoning, or examples provided to substantiate and strengthen the claims being made. Supports can take many forms, including empirical data, expert testimony, personal anecdotes, logical reasoning, and analogies. The quality and relevance of the supports provided play a critical role in the persuasiveness of the argument.

Continuing with the example of the argumentative essay about exercise, supports might include scientific studies demonstrating the health benefits of physical activity, testimonials from fitness experts, and personal stories of individuals who have experienced positive changes from incorporating exercise into their routine.

Warrants are the underlying assumptions or principles that connect the supports to the claims. They provide the reasoning or justification for why the supports are relevant and valid evidence for supporting the claims. Warrants are often implicit rather than explicit and require careful analysis to uncover. In the context of the essay on exercise, the warrant connecting the supports to the claim might be the assumption that actions that promote good health are inherently valuable and worthy of pursuit.

Rhetorical Analysis Essay Outline

Whether you opt for the option to buy essay or start writing it yourself, it's important to use a clear plan to organize your thoughts well. This plan usually includes four main steps, each looking at different parts of your analysis.

Analyzing the Text

Before writing a rhetorical analysis, take the time to thoroughly analyze the text you'll be examining. This means more than just skimming through it; it requires a thorough understanding of its subtleties and complexities. Here are some questions to guide your analysis:

• How does the text try to sway its audience? What methods does it use to convince or influence them?
• Which rhetorical appeals—ethos (credibility), pathos (emotion), logos (logic)—does the author use, and how do they contribute to the overall argument?
• What specific rhetorical devices and strategies does the author employ to effectively convey their message? Are there any patterns or recurring motifs?
• How does the structure of the text contribute to its persuasive power or overall impact?
• Are there any cultural, historical, or contextual factors that influence how the text is perceived or understood?

By scrutinizing the text in this manner, you'll gain a deeper understanding of how it functions and the techniques employed by the author to achieve their desired effect.

Rhetorical Analysis Introduction

The introduction sets the stage for your analysis by providing essential context and framing the discussion. Start by introducing the text you're analyzing, including the author's name and the title of the work. Provide some background information to give context to your analysis. For example, if you're analyzing a speech, mention the occasion or event where it was delivered.

Next, summarize the main arguments or claims made by the author. Highlight the rhetorical techniques they use to persuade their audience. Are they appealing to logic, emotion, credibility, or a combination of these? Use specific examples from the text to illustrate these techniques discussed by our dissertation service .

For instance, if you're analyzing a speech on climate change, mention the speaker's expertise in environmental science to establish credibility. Summarize the key points they make about the consequences of inaction and the urgent need for change.

Finally, conclude your introduction with a clear thesis statement. This statement should encapsulate the main argument or purpose of your analysis.

Rhetorical Analysis Body Paragraph

The body paragraphs form the crux of your analysis, where you delve into the details of the text and dissect its rhetorical strategies. Each paragraph should focus on a specific aspect of the text, such as the use of ethos, pathos, logos, or specific rhetorical devices.

Utilize Aristotle's rhetorical triangle and other key concepts introduced earlier to guide your analysis. Provide quotations or examples from the text to illustrate your points and explain why the author chose certain approaches. Evaluate the effectiveness of these strategies in achieving the author's goals and persuading the audience.

For instance, if you're discussing the use of pathos in a marketing campaign, analyze the emotional appeal of the imagery or language used and consider how it resonates with the target audience.

Rhetorical Analysis Conclusion

In the conclusion, it's crucial to reinforce your main arguments and evaluate the author's effectiveness in achieving their goals, whether you're writing an MLA or APA essay format . Reflect on the overall impact of the text on both its immediate audience and society at large, underscoring the importance of your analysis.

Resist the temptation to introduce new ideas in the conclusion. Instead, draw upon the points you've already explored in the body of your essay to strengthen your analysis. Conclude with a poignant statement that resonates with your readers, encapsulating the essence of your interpretation and leaving a lasting impression. This final remark should tie together the threads of your analysis, leaving the reader with a deeper understanding of the text's rhetorical strategies and significance.

Rhetorical Analysis Essay Example

In this section, you'll discover two essay samples that skillfully demonstrate the application of rhetorical analysis. These examples offer insightful insights into the effective use of rhetorical techniques in writing.

5 Rhetorical Analysis Essay Tips

Here are five focused tips that will help you lay a solid foundation for your examination.

• Dissect Rhetorical Strategies : Break down the text to identify specific rhetorical devices such as metaphor, simile, or parallelism.
• Evaluate Tone and Diction : Pay attention to the author's tone and word choice. Analyze how these elements contribute to the overall mood of the text.
• Probe Ethos, Pathos, Logos : Explore how the author establishes credibility (ethos), evokes emotions (pathos), and employs logic (logos) to sway the audience.
• Contextualize Historical Significance : Consider the historical, cultural, and social backdrop against which the text was written.
• Craft a Structured Analysis : Organize your essay with a clear introduction, body paragraphs focusing on specific rhetorical elements, and a conclusion that synthesizes your findings.

Final Words

As we near the end, it's important to analyze carefully whether you're examining a speech, an advertisement, or a story. Pay attention to the smart tactics that influence our thinking. It's all about revealing how we communicate and relate to one another. Ultimately, understanding rhetoric offers a fresh perspective on the world beyond just academic success.

Looking to Take Your Academic Performance to the Next Level?

Say goodbye to stress, endless research, and sleepless nights - and hello to a brighter academic future.

What is a Rhetorical Analysis Essay?

How to structure a rhetorical analysis essay, how to write a rhetorical analysis essay.

Daniel Parker

is a seasoned educational writer focusing on scholarship guidance, research papers, and various forms of academic essays including reflective and narrative essays. His expertise also extends to detailed case studies. A scholar with a background in English Literature and Education, Daniel’s work on EssayPro blog aims to support students in achieving academic excellence and securing scholarships. His hobbies include reading classic literature and participating in academic forums.

is an expert in nursing and healthcare, with a strong background in history, law, and literature. Holding advanced degrees in nursing and public health, his analytical approach and comprehensive knowledge help students navigate complex topics. On EssayPro blog, Adam provides insightful articles on everything from historical analysis to the intricacies of healthcare policies. In his downtime, he enjoys historical documentaries and volunteering at local clinics.

Related Articles

• PRO Courses Guides New Tech Help Pro Expert Videos About wikiHow Pro Upgrade Sign In
• EDIT Edit this Article
• EXPLORE Tech Help Pro About Us Random Article Quizzes Request a New Article Community Dashboard This Or That Game Popular Categories Arts and Entertainment Artwork Books Movies Computers and Electronics Computers Phone Skills Technology Hacks Health Men's Health Mental Health Women's Health Relationships Dating Love Relationship Issues Hobbies and Crafts Crafts Drawing Games Education & Communication Communication Skills Personal Development Studying Personal Care and Style Fashion Hair Care Personal Hygiene Youth Personal Care School Stuff Dating All Categories Arts and Entertainment Finance and Business Home and Garden Relationship Quizzes Cars & Other Vehicles Food and Entertaining Personal Care and Style Sports and Fitness Computers and Electronics Health Pets and Animals Travel Education & Communication Hobbies and Crafts Philosophy and Religion Work World Family Life Holidays and Traditions Relationships Youth
• Browse Articles
• Learn Something New
• Quizzes Hot
• This Or That Game
• Train Your Brain
• Explore More
• Support wikiHow
• About wikiHow
• Log in / Sign up
• Education and Communications
• College University and Postgraduate
• Academic Writing

How to Write a Rhetorical Analysis

Last Updated: April 2, 2024 Fact Checked

This article was co-authored by Megan Morgan, PhD . Megan Morgan is a Graduate Program Academic Advisor in the School of Public & International Affairs at the University of Georgia. She earned her PhD in English from the University of Georgia in 2015. This article has been fact-checked, ensuring the accuracy of any cited facts and confirming the authority of its sources. This article has been viewed 1,378,673 times.

A rhetorical analysis can be written about other texts, television shows, films, collections of artwork, or a variety of other communicative mediums that attempt to make a statement to an intended audience. In order to write a rhetorical analysis, you need to be able to determine how the creator of the original work attempts to make his or her argument. You can also include information about whether or not that argument is successful. To learn more about the right way to write a rhetorical analysis, continue reading.

Gathering Information

• The speaker refers to the first and last name of the writer. If the writer has any credentials that lend to his or her authority on the matter at hand, you should also briefly consider those. Note that if the narrator is different from the writer, though, it could also refer to the narrator.
• The occasion mostly refers to the type of text and the context under which the text was written. For instance, there is a big difference between an essay written for a scholarly conference and a letter written to an associate in the field.
• The audience is who the text was written for. This is related to the occasion, since the occasion can include details about the audience. In the example above, the audience would be a conference of scholars versus an associate in the field.
• The purpose refers to what the writer wants to accomplish in the text. It usually includes selling a product or point of view.
• The subject is simply the topic the writer discusses in the text.

• Ethos, or ethical appeals, rely on the writer's credibility and character in the garnering of approval. Mentions of a writer's character or qualifications usually qualify as ethos. For instance, if a family therapist with 20 years of practice writes an article on improving familial relations, mention of that experience would be using ethos. Despite their name, these appeals don't have anything to do with "ethics" as we usually think of them.
• Logos, or logical appeals, use reason to make an argument. Most academic discourse should make heavy use of logos. A writer who supports an argument with evidence, data, and undeniable facts uses logos.
• Pathos, or pathetic appeals, seek to evoke emotion in order to gain approval. These emotions can include anything from sympathy and anger to the desire for love. If an article about violent crime provides personal, human details about victims of violent crime, the writer is likely using pathos.

• Analogies and figurative language, including metaphors and similes, demonstrate an idea through comparison.
• Repetition of a certain point or idea is used to make that point seem more memorable.
• Imagery often affects pathos. The image of a starving child in a low income country can be a powerful way of evoking compassion or anger.
• Diction refers to word choice. Emotionally-charged words have greater impact, and rhythmic word patterns can establish a theme more effectively.
• Tone essentially means mood or attitude. A sarcastic essay is vastly different from a scientific one, but depending on the situation, either tone could be effective.
• Addressing the opposition demonstrates that the writer is not afraid of the opposing viewpoint. It also allows the writer to strengthen his or her own argument by cutting down the opposing one. This is especially powerful when the author contrasts a strong viewpoint he or she holds with a weak viewpoint on the opposing side.

• Ask yourself how the rhetorical strategies of appeals and style help the author achieve his or her purpose. Determine if any of these strategies fail and hurt the author instead of helping.
• Speculate on why the author may have chosen those rhetorical strategies for that audience and that occasion. Determine if the choice of strategies may have differed for a different audience or occasion.
• Remember that in a rhetorical analysis, you do not need to agree with the argument being presented. Your task is to analyze how well the author uses the appeals to present her or his argument.

Writing the Introduction

• By letting the reader know that your paper is a rhetorical analysis, you let him or her know exactly what to expect. If you do not let the reader know this information beforehand, he or she may expect to read an evaluative argument instead.
• Do not simply state, "This paper is a rhetorical analysis." Weave the information into the introduction as naturally as possible.
• Note that this may not be necessary if you are writing a rhetorical analysis for an assignment that specifically calls for a rhetorical analysis.

• The introduction is a good place to give a quick summary of the document. Keep it quick, though. Save the majority of the details for your body paragraphs, since most of the details will be used in defending your analysis.

• You do not necessarily need to mention these details in this order. Include the details in a matter that makes sense and flows naturally within your introductory paragraph.

• Try stating which rhetorical techniques the writer uses in order to move people toward his or her desired purpose. Analyze how well these techniques accomplish this goal.
• Consider narrowing the focus of your essay. Choose one or two design aspects that are complex enough to spend an entire essay analyzing.
• Think about making an original argument. If your analysis leads you to make a certain argument about the text, focus your thesis and essay around that argument and provide support for it throughout the body of your paper.
• Try to focus on using words such as "effective" or "ineffective" when composing your thesis, rather than "good" or "bad." You want to avoid seeming like you are passing value judgments.

Writing the Body

• The order of logos, ethos, and pathos is not necessarily set in stone. If you intend to focus on one more than the other two, you could briefly cover the two lesser appeals in the first two sections before elaborating on the third in greater detail toward the middle and end of the paper.
• For logos, identify at least one major claim and evaluate the document's use of objective evidence.
• For ethos, analyze how the writer or speaker uses his or her status as an "expert" to enhance credibility.
• For pathos, analyze any details that alter the way that the viewer or reader may feel about the subject at hand. Also analyze any imagery used to appeal to aesthetic senses, and determine how effective these elements are.
• Wrap things up by discussing the consequences and overall impact of these three appeals.

• Start from the beginning of the document and work your way through to the end. Present details about the document and your analysis of those details in the order the original document presents them in.
• The writer of the original document likely organized the information carefully and purposefully. By addressing the document in this order, your analysis is more likely to make more coherent sense by the end of your paper.

• Evidence often include a great deal of direct quotation and paraphrasing.
• Point to spots in which the author mentioned his or her credentials to explain ethos. Identify emotional images or words with strong emotional connotations as ways of supporting claims to pathos. Mention specific data and facts used in analysis involving logos.

• Avoid use of the first-person words "I" and "we." Stick to the more objective third-person.

Writing the Conclusion

• When restating your thesis, you should be able to quickly analyze how the original author's purpose comes together.
• When restating your thesis, try to bring more sophistication or depth to it than you had in the beginning. What can the audience now understand about your thesis that they would not have without reading your analysis?

• Keep this information brief. You spent an entire essay supporting your thesis, so these restatements of your main ideas should only serve as summaries of your support.

• Indicate what that research must entail and how it would help.
• Also state why the subject matter is important enough to continue researching and how it has significance to the real world.

Writing Help

Community Q&A

• Avoid the use of "In conclusion..." While many writers may be taught to end conclusion paragraphs with this phrase as they first learn to write essays, you should never include this phrase in an essay written at a higher academic level. This phrase and the information that usually follows it is empty information that only serves to clutter up your final paragraph. Thanks Helpful 0 Not Helpful 0
• Do not introduce any new information in your conclusion. Summarize the important details of the essay. Thanks Helpful 0 Not Helpful 0
• Do not argue in an analysis. Focus on the "how" they made their point, not if it's good or not. Thanks Helpful 0 Not Helpful 0

You Might Also Like

• ↑ https://owl.purdue.edu/owl/general_writing/academic_writing/establishing_arguments/rhetorical_strategies.html
• ↑ https://writingcenter.tamu.edu/Students/Writing-Speaking-Guides/Alphabetical-List-of-Guides/Academic-Writing/Analysis/Rhetorical-Analysis
• ↑ https://courses.lumenlearning.com/englishcomp1/chapter/text-an-overview-of-the-rhetorical-modes/
• ↑ https://oer.pressbooks.pub/informedarguments/chapter/rhetorical-modes-of-writing/
• ↑ https://owl.purdue.edu/owl/general_writing/visual_rhetoric/analyzing_visual_documents/organizing_your_analysis.html
• ↑ https://www.pfw.edu/offices/learning-support/documents/WriteARhetoricalAnalysis.pdf

About This Article

To write a rhetorical analysis, start by determining what the author of the work you're analyzing is trying to argue. Then, ask yourself if they succeeded in making their argument. Whether you think they did or didn't, include quotes and specific examples in your analysis to back up your opinion. When you're writing your analysis, use the third-person to appear objective as opposed to using "I" or "we." Also, make sure you include the author's name, profession, and purpose for writing the text at the beginning of your analysis to give reader's some context. To learn different ways to structure your rhetorical analysis from our English Ph.D. co-author, keep reading! Did this summary help you? Yes No

• Send fan mail to authors

Reader Success Stories

Dec 15, 2016

Did this article help you?

Theophilus Ndubisi Chukwu

Aug 13, 2016

Pamela Austin

Sep 28, 2017

John Cornelius

Jul 13, 2016

McKenzie Jameson

Oct 18, 2017

Featured Articles

Trending Articles

Watch Articles

• Terms of Use
• Privacy Policy
• Do Not Sell or Share My Info
• Not Selling Info

wikiHow Tech Help Pro:

Level up your tech skills and stay ahead of the curve

Purdue Online Writing Lab Purdue OWL® College of Liberal Arts

Organizing Your Analysis

Welcome to the Purdue OWL

This page is brought to you by the OWL at Purdue University. When printing this page, you must include the entire legal notice.

Copyright ©1995-2018 by The Writing Lab & The OWL at Purdue and Purdue University. All rights reserved. This material may not be published, reproduced, broadcast, rewritten, or redistributed without permission. Use of this site constitutes acceptance of our terms and conditions of fair use.

There is no one perfect way to organize a rhetorical analysis essay. In fact, writers should always be a bit leery of plug-in formulas that offer a perfect essay format. Remember, organization itself is not the enemy, only organization without considering the specific demands of your particular writing task. That said, here are some general tips for plotting out the overall form of your essay.

Introduction

Like any rhetorical analysis essay, an essay analyzing a visual document should quickly set the stage for what you’re doing. Try to cover the following concerns in the initial paragraphs:

• Make sure to let the reader know you’re performing a rhetorical analysis. Otherwise, they may expect you to take positions or make an evaluative argument that may not be coming.
• Clearly state what the document under consideration is and possibly give some pertinent background information about its history or development. The intro can be a good place for a quick, narrative summary of the document. The key word here is “quick, for you may be dealing with something large (for example, an entire episode of a cartoon like the Simpsons). Save more in-depth descriptions for your body paragraph analysis.
• If you’re dealing with a smaller document (like a photograph or an advertisement), and copyright allows, the introduction or first page is a good place to integrate it into your page.
• Give a basic run down of the rhetorical situation surrounding the document: the author, the audience, the purpose, the context, etc.

Thesis Statements and Focus

Many authors struggle with thesis statements or controlling ideas in regards to rhetorical analysis essays. There may be a temptation to think that merely announcing the text as a rhetorical analysis is purpose enough. However, especially depending on your essay’s length, your reader may need a more direct and clear statement of your intentions. Below are a few examples.

1. Clearly narrow the focus of what your essay will cover. Ask yourself if one or two design aspects of the document is interesting and complex enough to warrant a full analytical treatment.

The website for Amazon.com provides an excellent example of alignment and proximity to assist its visitors in navigating a potentially large and confusing amount of information.

2. Since visual documents often seek to move people towards a certain action (buying a product, attending an event, expressing a sentiment), an essay may analyze the rhetorical techniques used to accomplish this purpose. The thesis statement should reflect this goal.

The call-out flyer for the Purdue Rowing Team uses a mixture of dynamic imagery and tantalizing promises to create interest in potential, new members.

3. Rhetorical analysis can also easily lead to making original arguments. Performing the analysis may lead you to an argument; or vice versa, you may start with an argument and search for proof that supports it.

A close analysis of the female body images in the July 2007 issue of Cosmopolitan magazine reveals contradictions between the articles’ calls for self-esteem and the advertisements’ unrealistic, beauty demands.

These are merely suggestions. The best measure for what your focus and thesis statement should be the document itself and the demands of your writing situation. Remember that the main thrust of your thesis statement should be on how the document creates meaning and accomplishes its purposes. The OWl has additional information on writing thesis statements.

Analysis Order (Body Paragraphs)

Depending on the genre and size of the document under analysis, there are a number of logical ways to organize your body paragraphs. Below are a few possible options. Which ever you choose, the goal of your body paragraphs is to present parts of the document, give an extended analysis of how that part functions, and suggest how the part ties into a larger point (your thesis statement or goal).

Chronological

This is the most straight-forward approach, but it can also be effective if done for a reason (as opposed to not being able to think of another way). For example, if you are analyzing a photo essay on the web or in a booklet, a chronological treatment allows you to present your insights in the same order that a viewer of the document experiences those images. It is likely that the images have been put in that order and juxtaposed for a reason, so this line of analysis can be easily integrated into the essay.

Be careful using chronological ordering when dealing with a document that contains a narrative (i.e. a television show or music video). Focusing on the chronological could easily lead you to plot summary which is not the point of a rhetorical analysis.

A spatial ordering covers the parts of a document in the order the eye is likely to scan them. This is different than chronological order, for that is dictated by pages or screens where spatial order concerns order amongst a single page or plane. There are no unwavering guidelines for this, but you can use the following general guidelines.

• Left to right and top to down is still the normal reading and scanning pattern for English-speaking countries.
• The eye will naturally look for centers. This may be the technical center of the page or the center of the largest item on the page.
• Lines are often used to provide directions and paths for the eye to follow.
• Research has shown that on web pages, the eye tends to linger in the top left quadrant before moving left to right. Only after spending a considerable amount of time on the top, visible portion of the page will they then scroll down.

Persuasive Appeals

The classic, rhetorical appeals are logos, pathos, and ethos. These concepts roughly correspond to the logic, emotion, and character of the document’s attempt to persuade. You can find more information on these concepts elsewhere on the OWL. Once you understand these devices, you could potentially order your essay by analyzing the document’s use of logos, ethos, and pathos in different sections.

The conclusion of a rhetorical analysis essay may not operate too differently from the conclusion of any other kind of essay. Still, many writers struggle with what a conclusion should or should not do. You can find tips elsewhere on the OWL on writing conclusions. In short, however, you should restate your main ideas and explain why they are important; restate your thesis; and outline further research or work you believe should be completed to further your efforts.

Are you seeking one-on-one college counseling and/or essay support? Limited spots are now available. Click here to learn more.

How to Write the AP Lang Rhetorical Analysis Essay (With Example)

November 27, 2023

Feeling intimidated by the AP Lang Rhetorical Analysis Essay? We’re here to help demystify. Whether you’re cramming for the AP Lang exam right now or planning to take the test down the road, we’ve got crucial rubric information, helpful tips, and an essay example to prepare you for the big day. This post will cover 1) What is the AP Lang Rhetorical Analysis Essay? 2) AP Lang Rhetorical Analysis Rubric 3) AP Lang Rhetorical Analysis: Sample Prompt 4) AP Lang Rhetorical Analysis Essay Example 5)AP Lang Rhetorical Analysis Essay Example: Why It Works

What is the AP Lang Rhetorical Analysis Essay?

The AP Lang Rhetorical Analysis Essay is one of three essays included in the written portion of the AP English Exam. The full AP English Exam is 3 hours and 15 minutes long, with the first 60 minutes dedicated to multiple-choice questions. Once you complete the multiple-choice section, you move on to three equally weighted essays that ask you to synthesize, analyze, and interpret texts and develop well-reasoned arguments. The three essays include:

Synthesis essay: You’ll review various pieces of evidence and then write an essay that synthesizes (aka combines and interprets) the evidence and presents a clear argument. Read our write up on How to Write the AP Lang Synthesis Essay here.

Argumentative essay: You’ll take a stance on a specific topic and argue your case.

Rhetorical essay: You’ll read a provided passage, then analyze the author’s rhetorical choices and develop an argument that explains why the author made those rhetorical choices.

AP Lang Rhetorical Analysis Rubric

The AP Lang Rhetorical Analysis Essay is graded on just 3 rubric categories: Thesis, Evidence and Commentary, and Sophistication . At a glance, the rubric categories may seem vague, but AP exam graders are actually looking for very particular things in each category. We’ll break it down with dos and don’ts for each rubric category:

Thesis (0-1 point)

There’s nothing nebulous when it comes to grading AP Lang Rhetorical Analysis Essay thesis. You either have one or you don’t. Including a thesis gets you one point closer to a high score and leaving it out means you miss out on one crucial point. So, what makes a thesis that counts?

• Make sure your thesis argues something about the author’s rhetorical choices. Making an argument means taking a risk and offering your own interpretation of the provided text. This is an argument that someone else might disagree with.
• A good test to see if you have a thesis that makes an argument. In your head, add the phrase “I think that…” to the beginning of your thesis. If what follows doesn’t logically flow after that phrase (aka if what follows isn’t something you and only you think), it’s likely you’re not making an argument.
• Avoid a thesis that merely restates the prompt.
• Avoid a thesis that summarizes the text but does not make an argument.

Evidence and Commentary (0-4 points)

This rubric category is graded on a scale of 0-4 where 4 is the highest grade. Per the AP Lang Rhetorical Analysis rubric, to get a 4, you’ll want to:

• Include lots of specific evidence from the text. There is no set golden number of quotes to include, but you’ll want to make sure you’re incorporating more than a couple pieces of evidence that support your argument about the author’s rhetorical choices.
• Make sure you include more than one type of evidence, too. Let’s say you’re working on your essay and have gathered examples of alliteration to include as supporting evidence. That’s just one type of rhetorical choice, and it’s hard to make a credible argument if you’re only looking at one type of evidence. To fix that issue, reread the text again looking for patterns in word choice and syntax, meaningful figurative language and imagery, literary devices, and other rhetorical choices, looking for additional types of evidence to support your argument.
• After you include evidence, offer your own interpretation and explain how this evidence proves the point you make in your thesis.
• Don’t summarize or speak generally about the author and the text. Everything you write must be backed up with evidence.
• Don’t let quotes speak for themselves. After every piece of evidence you include, make sure to explain your interpretation. Also, connect the evidence to your overarching argument.

Sophistication (0-1 point)

In this case, sophistication isn’t about how many fancy vocabulary words or how many semicolons you use. According to College Board , one point can be awarded to AP Lang Rhetorical Analysis essays that “demonstrate sophistication of thought and/or a complex understanding of the rhetorical situation” in any of these three ways:

• Explaining the significance or relevance of the writer’s rhetorical choices.
• Explaining the purpose or function of the passage’s complexities or tensions.
• Employing a style that is consistently vivid and persuasive.

Note that you don’t have to achieve all three to earn your sophistication point. A good way to think of this rubric category is to consider it a bonus point that you can earn for going above and beyond in depth of analysis or by writing an especially persuasive, clear, and well-structured essay. In order to earn this point, you’ll need to first do a good job with your thesis, evidence, and commentary.

• Focus on nailing an argumentative thesis and multiple types of evidence. Getting these fundamentals of your essay right will set you up for achieving depth of analysis.
• Explain how each piece of evidence connects to your thesis.
• Spend a minute outlining your essay before you begin to ensure your essay flows in a clear and cohesive way.
• Steer clear of generalizations about the author or text.
• Don’t include arguments you can’t prove with evidence from the text.
• Avoid complex sentences and fancy vocabulary words unless you use them often. Long, clunky sentences with imprecisely used words are hard to follow.

AP Lang Rhetorical Analysis: Sample Prompt

The sample prompt below is published online by College Board and is a real example from the 2021 AP Exam. The prompt provides background context, essay instructions, and the text you need to analyze. For sake of space, we’ve included the text as an image you can click to read. After the prompt, we provide a sample high scoring essay and then explain why this AP Lang Rhetorical Analysis essay example works.

Suggested time—40 minutes.

(This question counts as one-third of the total essay section score.)

On February 27, 2013, while in office, former president Barack Obama delivered the following address dedicating the Rosa Parks statue in the National Statuary Hall of the United States Capitol building. Rosa Parks was an African American civil rights activist who was arrested in 1955 for refusing to give up her seat on a segregated bus in Montgomery, Alabama. Read the passage carefully. Write an essay that analyzes the rhetorical choices Obama makes to convey his message.

In your response you should do the following:

• Respond to the prompt with a thesis that analyzes the writer’s rhetorical choices.
• Select and use evidence to support your line of reasoning.
• Explain how the evidence supports your line of reasoning.
• Demonstrate an understanding of the rhetorical situation.
• Use appropriate grammar and punctuation in communicating your argument.

AP Lang Rhetorical Analysis Essay Example

In his speech delivered in 2013 at the dedication of Rosa Park’s statue, President Barack Obama acknowledges everything that Parks’ activism made possible in the United States. Telling the story of Parks’ life and achievements, Obama highlights the fact that Parks was a regular person whose actions accomplished enormous change during the civil rights era. Through the use of diction that portrays Parks as quiet and demure, long lists that emphasize the extent of her impacts, and Biblical references, Obama suggests that all of us are capable of achieving greater good, just as Parks did.

Although it might be a surprising way to start to his dedication, Obama begins his speech by telling us who Parks was not: “Rosa Parks held no elected office. She possessed no fortune” he explains in lines 1-2. Later, when he tells the story of the bus driver who threatened to have Parks arrested when she refused to get off the bus, he explains that Parks “simply replied, ‘You may do that’” (lines 22-23). Right away, he establishes that Parks was a regular person who did not hold a seat of power. Her protest on the bus was not part of a larger plan, it was a simple response. By emphasizing that Parks was not powerful, wealthy, or loud spoken, he implies that Parks’ style of activism is an everyday practice that all of us can aspire to.

AP Lang Rhetorical Analysis Essay Example (Continued)

Even though Obama portrays Parks as a demure person whose protest came “simply” and naturally, he shows the importance of her activism through long lists of ripple effects. When Parks challenged her arrest, Obama explains, Martin Luther King, Jr. stood with her and “so did thousands of Montgomery, Alabama commuters” (lines 27-28). They began a boycott that included “teachers and laborers, clergy and domestics, through rain and cold and sweltering heat, day after day, week after week, month after month, walking miles if they had to…” (lines 28-31). In this section of the speech, Obama’s sentences grow longer and he uses lists to show that Parks’ small action impacted and inspired many others to fight for change. Further, listing out how many days, weeks, and months the boycott lasted shows how Parks’ single act of protest sparked a much longer push for change.

To further illustrate Parks’ impact, Obama incorporates Biblical references that emphasize the importance of “that single moment on the bus” (lines 57-58). In lines 33-35, Obama explains that Parks and the other protestors are “driven by a solemn determination to affirm their God-given dignity” and he also compares their victory to the fall the “ancient walls of Jericho” (line 43). By of including these Biblical references, Obama suggests that Parks’ action on the bus did more than correct personal or political wrongs; it also corrected moral and spiritual wrongs. Although Parks had no political power or fortune, she was able to restore a moral balance in our world.

Toward the end of the speech, Obama states that change happens “not mainly through the exploits of the famous and the powerful, but through the countless acts of often anonymous courage and kindness” (lines 78-81). Through carefully chosen diction that portrays her as a quiet, regular person and through lists and Biblical references that highlight the huge impacts of her action, Obama illustrates exactly this point. He wants us to see that, just like Parks, the small and meek can change the world for the better.

AP Lang Rhetorical Analysis Essay Example: Why It Works

We would give the AP Lang Rhetorical Analysis essay above a score of 6 out of 6 because it fully satisfies the essay’s 3 rubric categories: Thesis, Evidence and Commentary, and Sophistication . Let’s break down what this student did:

The thesis of this essay appears in the last line of the first paragraph:

“ Through the use of diction that portrays Parks as quiet and demure, long lists that emphasize the extent of her impacts, and Biblical references, Obama suggests that all of us are capable of achieving greater good, just as Parks did .”

This student’s thesis works because they make a clear argument about Obama’s rhetorical choices. They 1) list the rhetorical choices that will be analyzed in the rest of the essay (the italicized text above) and 2) include an argument someone else might disagree with (the bolded text above).

Evidence and Commentary:

This student includes substantial evidence and commentary. Things they do right, per the AP Lang Rhetorical Analysis rubric:

• They include lots of specific evidence from the text in the form of quotes.
• They incorporate 3 different types of evidence (diction, long lists, Biblical references).
• After including evidence, they offer an interpretation of what the evidence means and explain how the evidence contributes to their overarching argument (aka their thesis).

Sophistication

This essay achieves sophistication according to the AP Lang Rhetorical Analysis essay rubric in a few key ways:

• This student provides an introduction that flows naturally into the topic their essay will discuss. Before they get to their thesis, they tell us that Obama portrays Parks as a “regular person” setting up their main argument: Obama wants all regular people to aspire to do good in the world just as Rosa Parks did.
• They organize evidence and commentary in a clear and cohesive way. Each body paragraph focuses on just one type of evidence.
• They explain how their evidence is significant. In the final sentence of each body paragraph, they draw a connection back to the overarching argument presented in the thesis.
• All their evidence supports the argument presented in their thesis. There is no extraneous evidence or misleading detail.
• They consider nuances in the text. Rather than taking the text at face value, they consider what Obama’s rhetorical choices imply and offer their own unique interpretation of those implications.
• In their final paragraph, they come full circle, reiterate their thesis, and explain what Obama’s rhetorical choices communicate to readers.
• Their sentences are clear and easy to read. There are no grammar errors or misused words.

AP Lang Rhetorical Analysis Essay—More Resources

Looking for more tips to help your master your AP Lang Rhetorical Analysis Essay? Brush up on 20 Rhetorical Devices High School Students Should Know and read our Tips for Improving Reading Comprehension . If you’re ready to start studying for another part of the AP English Exam, find more expert tips in our How to Write the AP Lang Synthesis blog post.

Considering what other AP classes to take? Read up on the Hardest AP Classes .

• High School Success

Christina Wood

Christina Wood holds a BA in Literature & Writing from UC San Diego, an MFA in Creative Writing from Washington University in St. Louis, and is currently a Doctoral Candidate in English at the University of Georgia, where she teaches creative writing and first-year composition courses. Christina has published fiction and nonfiction in numerous publications, including The Paris Review , McSweeney’s , Granta , Virginia Quarterly Review , The Sewanee Review , Mississippi Review , and Puerto del Sol , among others. Her story “The Astronaut” won the 2018 Shirley Jackson Award for short fiction and received a “Distinguished Stories” mention in the 2019 Best American Short Stories anthology.

• 2-Year Colleges
• Application Strategies
• Best Colleges by Major
• Best Colleges by State
• Big Picture
• Career & Personality Assessment
• College Essay
• College Search/Knowledge
• College Success
• Costs & Financial Aid
• Data Visualizations
• Dental School Admissions
• Extracurricular Activities
• Graduate School Admissions
• High Schools
• Homeschool Resources
• Law School Admissions
• Medical School Admissions
• Navigating the Admissions Process
• Online Learning
• Outdoor Adventure
• Private High School Spotlight
• Research Programs
• Summer Program Spotlight
• Summer Programs
• Teacher Tools
• Test Prep Provider Spotlight

“Innovative and invaluable…use this book as your college lifeline.”

— Lynn O'Shaughnessy

Nationally Recognized College Expert

College Planning in Your Inbox

Join our information-packed monthly newsletter.

Rhetorical Analysis Sample Essay

Harriet Clark

Ms. Rebecca Winter

13 Feb. 2015

Not Quite a Clean Sweep: Rhetorical Strategies in

Grose's "Cleaning: The Final Feminist Frontier”

A woman’s work is never done: many American women grow up with this saying and feel it to be true. 1 One such woman, author Jessica Grose, wrote “Cleaning: The Final Feminist Frontier,” published in 2013 in the New Republic, 2 and she argues that while the men recently started taking on more of the childcare and cooking, cleaning still falls unfairly on women. 3 Grose begins building her credibility with personal facts and reputable sources, citing convincing facts and statistics, and successfully employing emotional appeals; however, toward the end of the article, her attempts to appeal to readers’ emotions weaken her credibility and ultimately, her argument. 4

In her article, Grose first sets the stage by describing a specific scenario of house-cleaning with her husband after being shut in during Hurricane Sandy, and then she outlines the uneven distribution of cleaning work in her marriage and draws a comparison to the larger feminist issue of who does the cleaning in a relationship. Grose continues by discussing some of the reasons that men do not contribute to cleaning: the praise for a clean house goes to the woman; advertising and media praise men’s cooking and childcare, but not cleaning; and lastly, it is just not fun. Possible solutions to the problem, Grose suggests, include making a chart of who does which chores, dividing up tasks based on skill and ability, accepting a dirtier home, and making cleaning more fun with gadgets. 5

Throughout her piece, Grose uses many strong sources that strengthen her credibility and appeal to ethos, as well as build her argument. 6 These sources include, “sociologists Judith Treas and Tsui-o Tai,” “a 2008 study from the University of New Hampshire,” and “P&G North America Fabric Care Brand Manager, Matthew Krehbiel” (qtd. in Grose). 7 Citing these sources boosts Grose’s credibility by showing that she has done her homework and has provided facts and statistics, as well as expert opinions to support her claim. She also uses personal examples from her own home life to introduce and support the issue, which shows that she has a personal stake in and first-hand experience with the problem. 8

Adding to her ethos appeals, Grose uses strong appeals to logos, with many facts and statistics and logical progressions of ideas. 9 She points out facts about her marriage and the distribution of household chores: “My husband and I both work. We split midnight baby feedings ...but ... he will admit that he’s never cleaned the bathroom, that I do the dishes nine times out of ten, and that he barely knows how the washer and dryer work in the apartment we’ve lived in for over eight months.” 10 These facts introduce and support the idea that Grose does more household chores than her husband. Grose continues with many statistics:

[A]bout 55 percent of American mothers employed full time do some housework on an average day, while only 18 percent of employed fathers do. ... [W]orking women with children are still doing a week and a half more of “second shift” work each year than their male partners. ... Even in the famously gender-neutral Sweden, women do 45 minutes more housework a day than their male partners. 11

These statistics are a few of many that logically support her claim that it is a substantial and real problem that men do not do their fair share of the chores. The details and numbers build an appeal to logos and impress upon the reader that this is a problem worth discussing. 12

Along with strong logos appeals, Grose effectively makes appeals to pathos in the beginning and middle sections. 13 Her introduction is full of emotionally-charged words and phrases that create a sympathetic image; Grose notes that she “was eight months pregnant” and her husband found it difficult to “fight with a massively pregnant person.” 14 The image she evokes of the challenges and vulnerabilities of being so pregnant, as well as the high emotions a woman feels at that time effectively introduce the argument and its seriousness. Her goal is to make the reader feel sympathy for her. Adding to this idea are words and phrases such as, “insisted,” “argued,” “not fun,” “sucks” “headachey,” “be judged,” “be shunned” (Grose). All of these words evoke negative emotions about cleaning, which makes the reader sympathize with women who feel “judged” and shunned”—very negative feelings. Another feeling Grose reinforces with her word choice is the concept of fairness: “fair share,” “a week and a half more of ‘second shift’ work,” “more housework,” “more gendered and less frequent.” These words help establish the unfairness that exists when women do all of the cleaning, and they are an appeal to pathos, or the readers’ feelings of frustration and anger with injustice. 15

However, the end of the article lacks the same level of effectiveness in the appeals to ethos. 16 For example, Grose notes that when men do housework, they are considered to be “’enacting “small instances of gender heroism,” or ‘SIGH’s’—which, barf.” 17 The usage of the word “barf” is jarring to the reader; unprofessional and immature, it is a shift from the researched, intelligent voice she has established and the reader is less likely to take the author seriously. This damages the strength of her credibility and her argument. 18

Additionally, her last statement in the article refers to her husband in a way that weakens the argument. 19 While returning to the introduction’s hook in the conclusion is a frequently-used strategy, Grose chooses to return to her discussion of her husband in a humorous way: Grose discusses solutions, and says there is “a huge, untapped market ... for toilet-scrubbing iPods. I bet my husband would buy one.” 20 Returning to her own marriage and husband is an appeal to ethos or personal credibility, and while that works well in the introduction, in the conclusion, it lacks the strength and seriousness that the topic deserves and was given earlier in the article. 21

Though Grose begins the essay by effectively persuading her readers of the unfair distribution of home-maintenance cleaning labor, she loses her power in the end, where she most needs to drive home her argument. Readers can see the problem exists in both her marriage and throughout the world; however, her shift to humor and sarcasm makes the reader not take the problem as seriously in the end. 22 Grose could have more seriously driven home the point that a woman’s work could be done: by a man. 23

Works Cited

Grose, Jessica. “Cleaning: The Final Feminist Frontier.” New Republic. The New Republic, 19 Mar. 2013. Web. 28 Mar. 2014.

• Article author's claim or purpose
• Summary of the article's main point in the second paragraph (could also be in the introduction)
• Third paragraph begins with a transition and topic sentence that reflects the first topic in the thesis
• Quotes illustrate how the author uses appeals to ethos
• Analysis explains how the quotes show the effective use of ethos as noted in the thesis
• Transition and topic sentence about the second point from the thesis
• Quote that illustrates appeals to logos
• Analysis explains how the quotes show the effective use of logos, as noted in the thesis
• Transition and topic sentence about the third point from the thesis
• Quotes that illustrate appeals to pathos
• Analysis explains how the quotes show the effective use of pathos, as noted in the thesis
• Transition and topic sentence about fourth point from the thesis
• Quote illustrates how the author uses appeal to ethos
• Analysis explains how quote supports thesis
• Transition and topic sentence about fourth point from thesis
• Conclusion returns to the ideas in the thesis and further develops them
• Last sentence returns to the hook in the introduction

Learn more about the " Rhetorical Analysis Graphic Organizer ."

Learn more about " Pathos, Logos, and Ethos ."

• Our Writers
• How to Order
• Assignment Writing Service
• Report Writing Service
• Buy Coursework
• Dissertation Writing Service
• Research Paper Writing Service
• All Essay Services
• Buy Research Paper
• Buy Term Paper
• Buy Dissertation
• Buy Case study
• Buy Presentation
• Buy Personal statement

Rhetorical Analysis Essay

Rhetorical Analysis Essay Example

Rhetorical Analysis Essay Example - Free Samples

11 min read

People also read

Rhetorical Analysis Essay - A Complete Guide With Examples

320+ Best Rhetorical Analysis Essay Topics

Crafting an Effective Rhetorical Analysis Essay Outline - Free Samples!

Ethos, Pathos, and Logos - Structure, Usage & Examples

Writing a rhetorical analysis essay for academics can be really demanding for students. This type of paper requires high-level analyzing abilities and professional writing skills to be drafted effectively.

As this essay persuades the audience, it is essential to know how to take a strong stance and develop a thesis. 

This article will find some examples that will help you with your rhetorical analysis essay writing effortlessly. 

• 1. Good Rhetorical Analysis Essay Example
• 2. Rhetorical Analysis Essay Example AP Lang 2023
• 3. Rhetorical Analysis Essay Examples for Students 
• 4. Writing a Visual Rhetorical Analysis Essay with Example 
• 5. Rhetorical Analysis Essay Writing Tips

Good Rhetorical Analysis Essay Example

The step-by-step writing process of a rhetorical analysis essay is far more complicated than ordinary academic essays. This essay type critically analyzes the rhetorical means used to persuade the audience and their efficiency. 

The example provided below is the best rhetorical analysis essay example:

Rhetorical Analysis Essay Sample

In this essay type, the author uses rhetorical approaches such as ethos, pathos, and logos .  These approaches are then studied and analyzed deeply by the essay writers to weigh their effectiveness in delivering the message.

Let’s take a look at the following example to get a better idea;

The outline and structure of a rhetorical analysis essay are important. 

According to the essay outline, the essay is divided into three sections: 

• Introduction
• Ethos 
• Logos 

A rhetorical analysis essay outline is the same as the traditional one. The different parts of the rhetorical analysis essay are written in the following way:

Rhetorical Analysis Introduction Example

The introductory paragraph of a rhetorical analysis essay is written for the following purpose:

• To provide basic background information about the chosen author and the text.
• Identify the target audience of the essay. 

An introduction for a rhetorical essay is drafted by:

• Stating an opening sentence known as the hook statement. This catchy sentence is prepared to grab the audience’s attention to the paper. 
• After the opening sentence, the background information of the author and the original text are provided. 

For example, a rhetorical analysis essay written by Lee Jennings on“The Right Stuff” by David Suzuki. Lee started the essay by providing the introduction in the following way:

Analysis of the Example: 

• Suzuki stresses the importance of high school education. He prepares his readers for a proposal to make that education as valuable as possible.
• A rhetorical analysis can show how successful Suzuki was in using logos, pathos, and ethos. He had a strong ethos because of his reputation. 
• He also used pathos to appeal to parents and educators. However, his use of logos could have been more successful.
• Here Jennings stated the background information about the text and highlighted the rhetorical techniques used and their effectiveness. 

Thesis Statement Example for Rhetorical Analysis Essay 

A thesis statement of a rhetorical analysis essay is the writer’s stance on the original text. It is the argument that a writer holds and proves it using the evidence from the original text. 

A thesis statement for a rhetorical essay is written by analyzing the following elements of the original text:

• Diction - It refers to the author’s choice of words and the tone
• Imagery - The visual descriptive language that the author used in the content. 
• Simile - The comparison of things and ideas

In Jennings's analysis of “The Right Stuff,” the thesis statement was:

Example For Rhetorical Analysis Thesis Statement

Rhetorical Analysis Body Paragraph Example 

In the body paragraphs of your rhetorical analysis essay, you dissect the author's work, analyze their use of rhetorical techniques, and provide evidence to support your analysis. 

Let's look at an example that analyzes the use of ethos in David Suzuki's essay:

Rhetorical Analysis Conclusion Example

All the body paragraphs lead the audience towards the conclusion.

For example, the conclusion of “The Right Stuff” is written in the following way by Jennings:

In the conclusion section, Jennings summarized the major points and restated the thesis statement to prove them. 

Rhetorical Essay Example For The Right Stuff by David Suzuki

Rhetorical Analysis Essay Example AP Lang 2023

Writing a rhetorical analysis for the AP Language and Composition course can be challenging. So drafting it correctly is important to earn good grades. 

To make your essay effective and winning, follow the tips provided by professionals below:

Step #1: Understand the Prompt

Understanding the prompt is the first thing to produce an influential rhetorical paper. It is mandatory for this academic writing to read and understand the prompt to know what the task demands from you. 

Step #2: Stick to the Format

The content for the rhetorical analysis should be appropriately organized and structured. For this purpose, a proper outline is drafted. 

The rhetorical analysis essay outline divides all the information into different sections, such as the introduction, body, and conclusion.  The introduction should explicitly state the background information and the thesis statement. 

All the body paragraphs should start with a topic sentence to convey a claim to the readers. Provide a thorough analysis of these claims in the paragraph to support your topic sentence. 

Step #3: Use Rhetorical Elements to Form an Argument 

Analyze the following things in the text to form an argument for your essay:

• Language (tone and words)
• Organizational structure
• Rhetorical Appeals ( ethos, pathos, and logos) 

Once you have analyzed the rhetorical appeals and other devices like imagery and diction, you can form a strong thesis statement. The thesis statement will be the foundation on which your essay will be standing. 

AP Language Rhetorical Essay Sample

AP Rhetorical Analysis Essay Template

Rhetorical Analysis Essay Example AP Lang

AP Lang Rhetorical Analysis Essay Example

Rhetorical Analysis Essay Examples for Students 

Here are a few more examples to help the students write a rhetorical analysis essay:

Rhetorical Analysis Essay Example Ethos, Pathos, Logos

Rhetorical Analysis Essay Example Outline

Rhetorical Analysis Essay Example College

Rhetorical Analysis Essay Example APA Format

Compare and Contrast Rhetorical Analysis Essay Example

Comparative Rhetorical Analysis Essay Example

How to Start Rhetorical Analysis Essay Example

Rhetorical Analysis Essay Example High School

Rhetorical Analysis Essay Example APA Sample

Rhetorical Analysis Essay Example Of a Song

Florence Kelley Speech Rhetorical Analysis Essay Example

Rhetorical Analysis Essay Example MLA

Writing a Visual Rhetorical Analysis Essay with Example 

The visual rhetorical analysis essay determines how pictures and images communicate messages and persuade the audience. 

Usually, visual rhetorical analysis papers are written for advertisements. This is because they use strong images to convince the audience to behave in a certain way. 

To draft a perfect visual rhetorical analysis essay, follow the tips below:

• Analyze the advertisement deeply and note every minor detail. 
• Notice objects and colors used in the image to gather every detail.
• Determine the importance of the colors and objects and analyze why the advertiser chose the particular picture. 
• See what you feel about the image.
• Consider the objective of the image. Identify the message that the image is portraying. 
• Identify the targeted audience and how they respond to the picture. 

An example is provided below to give students a better idea of the concept. 

Simplicity Breeds Clarity Visual Rhetorical Analysis Essay Example

Rhetorical Analysis Essay Writing Tips

Follow the tips provided below to make your rhetorical writing compelling. 

• Choose an engaging topic for your essay. The rhetorical analysis essay topic should be engaging to grab the reader’s attention.
• Thoroughly read the original text.
• Identify the SOAPSTone. From the text, determine the speaker, occasions, audience, purpose, subject, and tone.
• Develop a thesis statement to state your claim over the text.
• Draft a rhetorical analysis essay outline.
• Write an engaging essay introduction by giving a hook statement and background information. At the end of the introductory paragraph, state the thesis statement.
• The body paragraphs of the rhetorical essay should have a topic sentence. Also, in the paragraph, a thorough analysis should be presented.
• For writing a satisfactory rhetorical essay conclusion, restate the thesis statement and summarize the main points.
• Proofread your essay to check for mistakes in the content. Make your edits before submitting the draft.

Following the tips and the essay's correct writing procedure will guarantee success in your academics. 

We have given you plenty of examples of a rhetorical analysis essay. But if you are still struggling to draft a great rhetorical analysis essay, it is suggested to take a professional’s help.

MyPerfectWords.com can assist you with all your academic assignments. The top essay writer service that we provide is reliable. If you are confused about your writing assignments and have difficulty meeting the deadline, get help from custom essay writing online .

Hire our analytical essay writing service today at the most reasonable prices. 

Write Essay Within 60 Seconds!

Nova Allison is a Digital Content Strategist with over eight years of experience. Nova has also worked as a technical and scientific writer. She is majorly involved in developing and reviewing online content plans that engage and resonate with audiences. Nova has a passion for writing that engages and informs her readers.

Paper Due? Why Suffer? That’s our Job!

Keep reading

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 03 June 2024

Applying large language models for automated essay scoring for non-native Japanese

• Wenchao Li 1 &
• Haitao Liu 2  

Humanities and Social Sciences Communications volume  11 , Article number:  723 ( 2024 ) Cite this article

1 Altmetric

Metrics details

• Language and linguistics

Recent advancements in artificial intelligence (AI) have led to an increased use of large language models (LLMs) for language assessment tasks such as automated essay scoring (AES), automated listening tests, and automated oral proficiency assessments. The application of LLMs for AES in the context of non-native Japanese, however, remains limited. This study explores the potential of LLM-based AES by comparing the efficiency of different models, i.e. two conventional machine training technology-based methods (Jess and JWriter), two LLMs (GPT and BERT), and one Japanese local LLM (Open-Calm large model). To conduct the evaluation, a dataset consisting of 1400 story-writing scripts authored by learners with 12 different first languages was used. Statistical analysis revealed that GPT-4 outperforms Jess and JWriter, BERT, and the Japanese language-specific trained Open-Calm large model in terms of annotation accuracy and predicting learning levels. Furthermore, by comparing 18 different models that utilize various prompts, the study emphasized the significance of prompts in achieving accurate and reliable evaluations using LLMs.

Similar content being viewed by others

Scoring method of English composition integrating deep learning in higher vocational colleges

ChatGPT-3.5 as writing assistance in students’ essays

Detecting contract cheating through linguistic fingerprint

Conventional machine learning technology in aes.

AES has experienced significant growth with the advancement of machine learning technologies in recent decades. In the earlier stages of AES development, conventional machine learning-based approaches were commonly used. These approaches involved the following procedures: a) feeding the machine with a dataset. In this step, a dataset of essays is provided to the machine learning system. The dataset serves as the basis for training the model and establishing patterns and correlations between linguistic features and human ratings. b) the machine learning model is trained using linguistic features that best represent human ratings and can effectively discriminate learners’ writing proficiency. These features include lexical richness (Lu, 2012 ; Kyle and Crossley, 2015 ; Kyle et al. 2021 ), syntactic complexity (Lu, 2010 ; Liu, 2008 ), text cohesion (Crossley and McNamara, 2016 ), and among others. Conventional machine learning approaches in AES require human intervention, such as manual correction and annotation of essays. This human involvement was necessary to create a labeled dataset for training the model. Several AES systems have been developed using conventional machine learning technologies. These include the Intelligent Essay Assessor (Landauer et al. 2003 ), the e-rater engine by Educational Testing Service (Attali and Burstein, 2006 ; Burstein, 2003 ), MyAccess with the InterlliMetric scoring engine by Vantage Learning (Elliot, 2003 ), and the Bayesian Essay Test Scoring system (Rudner and Liang, 2002 ). These systems have played a significant role in automating the essay scoring process and providing quick and consistent feedback to learners. However, as touched upon earlier, conventional machine learning approaches rely on predetermined linguistic features and often require manual intervention, making them less flexible and potentially limiting their generalizability to different contexts.

In the context of the Japanese language, conventional machine learning-incorporated AES tools include Jess (Ishioka and Kameda, 2006 ) and JWriter (Lee and Hasebe, 2017 ). Jess assesses essays by deducting points from the perfect score, utilizing the Mainichi Daily News newspaper as a database. The evaluation criteria employed by Jess encompass various aspects, such as rhetorical elements (e.g., reading comprehension, vocabulary diversity, percentage of complex words, and percentage of passive sentences), organizational structures (e.g., forward and reverse connection structures), and content analysis (e.g., latent semantic indexing). JWriter employs linear regression analysis to assign weights to various measurement indices, such as average sentence length and total number of characters. These weights are then combined to derive the overall score. A pilot study involving the Jess model was conducted on 1320 essays at different proficiency levels, including primary, intermediate, and advanced. However, the results indicated that the Jess model failed to significantly distinguish between these essay levels. Out of the 16 measures used, four measures, namely median sentence length, median clause length, median number of phrases, and maximum number of phrases, did not show statistically significant differences between the levels. Additionally, two measures exhibited between-level differences but lacked linear progression: the number of attributives declined words and the Kanji/kana ratio. On the other hand, the remaining measures, including maximum sentence length, maximum clause length, number of attributive conjugated words, maximum number of consecutive infinitive forms, maximum number of conjunctive-particle clauses, k characteristic value, percentage of big words, and percentage of passive sentences, demonstrated statistically significant between-level differences and displayed linear progression.

Both Jess and JWriter exhibit notable limitations, including the manual selection of feature parameters and weights, which can introduce biases into the scoring process. The reliance on human annotators to label non-native language essays also introduces potential noise and variability in the scoring. Furthermore, an important concern is the possibility of system manipulation and cheating by learners who are aware of the regression equation utilized by the models (Hirao et al. 2020 ). These limitations emphasize the need for further advancements in AES systems to address these challenges.

Deep learning technology in AES

Deep learning has emerged as one of the approaches for improving the accuracy and effectiveness of AES. Deep learning-based AES methods utilize artificial neural networks that mimic the human brain’s functioning through layered algorithms and computational units. Unlike conventional machine learning, deep learning autonomously learns from the environment and past errors without human intervention. This enables deep learning models to establish nonlinear correlations, resulting in higher accuracy. Recent advancements in deep learning have led to the development of transformers, which are particularly effective in learning text representations. Noteworthy examples include bidirectional encoder representations from transformers (BERT) (Devlin et al. 2019 ) and the generative pretrained transformer (GPT) (OpenAI).

BERT is a linguistic representation model that utilizes a transformer architecture and is trained on two tasks: masked linguistic modeling and next-sentence prediction (Hirao et al. 2020 ; Vaswani et al. 2017 ). In the context of AES, BERT follows specific procedures, as illustrated in Fig. 1 : (a) the tokenized prompts and essays are taken as input; (b) special tokens, such as [CLS] and [SEP], are added to mark the beginning and separation of prompts and essays; (c) the transformer encoder processes the prompt and essay sequences, resulting in hidden layer sequences; (d) the hidden layers corresponding to the [CLS] tokens (T[CLS]) represent distributed representations of the prompts and essays; and (e) a multilayer perceptron uses these distributed representations as input to obtain the final score (Hirao et al. 2020 ).

AES system with BERT (Hirao et al. 2020 ).

The training of BERT using a substantial amount of sentence data through the Masked Language Model (MLM) allows it to capture contextual information within the hidden layers. Consequently, BERT is expected to be capable of identifying artificial essays as invalid and assigning them lower scores (Mizumoto and Eguchi, 2023 ). In the context of AES for nonnative Japanese learners, Hirao et al. ( 2020 ) combined the long short-term memory (LSTM) model proposed by Hochreiter and Schmidhuber ( 1997 ) with BERT to develop a tailored automated Essay Scoring System. The findings of their study revealed that the BERT model outperformed both the conventional machine learning approach utilizing character-type features such as “kanji” and “hiragana”, as well as the standalone LSTM model. Takeuchi et al. ( 2021 ) presented an approach to Japanese AES that eliminates the requirement for pre-scored essays by relying solely on reference texts or a model answer for the essay task. They investigated multiple similarity evaluation methods, including frequency of morphemes, idf values calculated on Wikipedia, LSI, LDA, word-embedding vectors, and document vectors produced by BERT. The experimental findings revealed that the method utilizing the frequency of morphemes with idf values exhibited the strongest correlation with human-annotated scores across different essay tasks. The utilization of BERT in AES encounters several limitations. Firstly, essays often exceed the model’s maximum length limit. Second, only score labels are available for training, which restricts access to additional information.

Mizumoto and Eguchi ( 2023 ) were pioneers in employing the GPT model for AES in non-native English writing. Their study focused on evaluating the accuracy and reliability of AES using the GPT-3 text-davinci-003 model, analyzing a dataset of 12,100 essays from the corpus of nonnative written English (TOEFL11). The findings indicated that AES utilizing the GPT-3 model exhibited a certain degree of accuracy and reliability. They suggest that GPT-3-based AES systems hold the potential to provide support for human ratings. However, applying GPT model to AES presents a unique natural language processing (NLP) task that involves considerations such as nonnative language proficiency, the influence of the learner’s first language on the output in the target language, and identifying linguistic features that best indicate writing quality in a specific language. These linguistic features may differ morphologically or syntactically from those present in the learners’ first language, as observed in (1)–(3).

我-送了-他-一本-书

Wǒ-sòngle-tā-yī běn-shū

1 sg .-give. past- him-one .cl- book

“I gave him a book.”

Agglutinative

彼-に-本-を-あげ-まし-た

Kare-ni-hon-o-age-mashi-ta

3 sg .- dat -hon- acc- give.honorification. past

Inflectional

give, give-s, gave, given, giving

Additionally, the morphological agglutination and subject-object-verb (SOV) order in Japanese, along with its idiomatic expressions, pose additional challenges for applying language models in AES tasks (4).

足-が 棒-に なり-ました

Ashi-ga bo-ni nar-mashita

leg- nom stick- dat become- past

“My leg became like a stick (I am extremely tired).”

The example sentence provided demonstrates the morpho-syntactic structure of Japanese and the presence of an idiomatic expression. In this sentence, the verb “なる” (naru), meaning “to become”, appears at the end of the sentence. The verb stem “なり” (nari) is attached with morphemes indicating honorification (“ます” - mashu) and tense (“た” - ta), showcasing agglutination. While the sentence can be literally translated as “my leg became like a stick”, it carries an idiomatic interpretation that implies “I am extremely tired”.

To overcome this issue, CyberAgent Inc. ( 2023 ) has developed the Open-Calm series of language models specifically designed for Japanese. Open-Calm consists of pre-trained models available in various sizes, such as Small, Medium, Large, and 7b. Figure 2 depicts the fundamental structure of the Open-Calm model. A key feature of this architecture is the incorporation of the Lora Adapter and GPT-NeoX frameworks, which can enhance its language processing capabilities.

GPT-NeoX Model Architecture (Okgetheng and Takeuchi 2024 ).

In a recent study conducted by Okgetheng and Takeuchi ( 2024 ), they assessed the efficacy of Open-Calm language models in grading Japanese essays. The research utilized a dataset of approximately 300 essays, which were annotated by native Japanese educators. The findings of the study demonstrate the considerable potential of Open-Calm language models in automated Japanese essay scoring. Specifically, among the Open-Calm family, the Open-Calm Large model (referred to as OCLL) exhibited the highest performance. However, it is important to note that, as of the current date, the Open-Calm Large model does not offer public access to its server. Consequently, users are required to independently deploy and operate the environment for OCLL. In order to utilize OCLL, users must have a PC equipped with an NVIDIA GeForce RTX 3060 (8 or 12 GB VRAM).

In summary, while the potential of LLMs in automated scoring of nonnative Japanese essays has been demonstrated in two studies—BERT-driven AES (Hirao et al. 2020 ) and OCLL-based AES (Okgetheng and Takeuchi, 2024 )—the number of research efforts in this area remains limited.

Another significant challenge in applying LLMs to AES lies in prompt engineering and ensuring its reliability and effectiveness (Brown et al. 2020 ; Rae et al. 2021 ; Zhang et al. 2021 ). Various prompting strategies have been proposed, such as the zero-shot chain of thought (CoT) approach (Kojima et al. 2022 ), which involves manually crafting diverse and effective examples. However, manual efforts can lead to mistakes. To address this, Zhang et al. ( 2021 ) introduced an automatic CoT prompting method called Auto-CoT, which demonstrates matching or superior performance compared to the CoT paradigm. Another prompt framework is trees of thoughts, enabling a model to self-evaluate its progress at intermediate stages of problem-solving through deliberate reasoning (Yao et al. 2023 ).

Beyond linguistic studies, there has been a noticeable increase in the number of foreign workers in Japan and Japanese learners worldwide (Ministry of Health, Labor, and Welfare of Japan, 2022 ; Japan Foundation, 2021 ). However, existing assessment methods, such as the Japanese Language Proficiency Test (JLPT), J-CAT, and TTBJ Footnote 1 , primarily focus on reading, listening, vocabulary, and grammar skills, neglecting the evaluation of writing proficiency. As the number of workers and language learners continues to grow, there is a rising demand for an efficient AES system that can reduce costs and time for raters and be utilized for employment, examinations, and self-study purposes.

This study aims to explore the potential of LLM-based AES by comparing the effectiveness of five models: two LLMs (GPT Footnote 2 and BERT), one Japanese local LLM (OCLL), and two conventional machine learning-based methods (linguistic feature-based scoring tools - Jess and JWriter).

The research questions addressed in this study are as follows:

To what extent do the LLM-driven AES and linguistic feature-based AES, when used as automated tools to support human rating, accurately reflect test takers’ actual performance?

What influence does the prompt have on the accuracy and performance of LLM-based AES methods?

The subsequent sections of the manuscript cover the methodology, including the assessment measures for nonnative Japanese writing proficiency, criteria for prompts, and the dataset. The evaluation section focuses on the analysis of annotations and rating scores generated by LLM-driven and linguistic feature-based AES methods.

Methodology

The dataset utilized in this study was obtained from the International Corpus of Japanese as a Second Language (I-JAS) Footnote 3 . This corpus consisted of 1000 participants who represented 12 different first languages. For the study, the participants were given a story-writing task on a personal computer. They were required to write two stories based on the 4-panel illustrations titled “Picnic” and “The key” (see Appendix A). Background information for the participants was provided by the corpus, including their Japanese language proficiency levels assessed through two online tests: J-CAT and SPOT. These tests evaluated their reading, listening, vocabulary, and grammar abilities. The learners’ proficiency levels were categorized into six levels aligned with the Common European Framework of Reference for Languages (CEFR) and the Reference Framework for Japanese Language Education (RFJLE): A1, A2, B1, B2, C1, and C2. According to Lee et al. ( 2015 ), there is a high level of agreement (r = 0.86) between the J-CAT and SPOT assessments, indicating that the proficiency certifications provided by J-CAT are consistent with those of SPOT. However, it is important to note that the scores of J-CAT and SPOT do not have a one-to-one correspondence. In this study, the J-CAT scores were used as a benchmark to differentiate learners of different proficiency levels. A total of 1400 essays were utilized, representing the beginner (aligned with A1), A2, B1, B2, C1, and C2 levels based on the J-CAT scores. Table 1 provides information about the learners’ proficiency levels and their corresponding J-CAT and SPOT scores.

A dataset comprising a total of 1400 essays from the story writing tasks was collected. Among these, 714 essays were utilized to evaluate the reliability of the LLM-based AES method, while the remaining 686 essays were designated as development data to assess the LLM-based AES’s capability to distinguish participants with varying proficiency levels. The GPT 4 API was used in this study. A detailed explanation of the prompt-assessment criteria is provided in Section Prompt . All essays were sent to the model for measurement and scoring.

Measures of writing proficiency for nonnative Japanese

Japanese exhibits a morphologically agglutinative structure where morphemes are attached to the word stem to convey grammatical functions such as tense, aspect, voice, and honorifics, e.g. (5).

食べ-させ-られ-まし-た-か

tabe-sase-rare-mashi-ta-ka

[eat (stem)-causative-passive voice-honorification-tense. past-question marker]

Japanese employs nine case particles to indicate grammatical functions: the nominative case particle が (ga), the accusative case particle を (o), the genitive case particle の (no), the dative case particle に (ni), the locative/instrumental case particle で (de), the ablative case particle から (kara), the directional case particle へ (e), and the comitative case particle と (to). The agglutinative nature of the language, combined with the case particle system, provides an efficient means of distinguishing between active and passive voice, either through morphemes or case particles, e.g. 食べる taberu “eat concusive . ” (active voice); 食べられる taberareru “eat concusive . ” (passive voice). In the active voice, “パン を 食べる” (pan o taberu) translates to “to eat bread”. On the other hand, in the passive voice, it becomes “パン が 食べられた” (pan ga taberareta), which means “(the) bread was eaten”. Additionally, it is important to note that different conjugations of the same lemma are considered as one type in order to ensure a comprehensive assessment of the language features. For example, e.g., 食べる taberu “eat concusive . ”; 食べている tabeteiru “eat progress .”; 食べた tabeta “eat past . ” as one type.

To incorporate these features, previous research (Suzuki, 1999 ; Watanabe et al. 1988 ; Ishioka, 2001 ; Ishioka and Kameda, 2006 ; Hirao et al. 2020 ) has identified complexity, fluency, and accuracy as crucial factors for evaluating writing quality. These criteria are assessed through various aspects, including lexical richness (lexical density, diversity, and sophistication), syntactic complexity, and cohesion (Kyle et al. 2021 ; Mizumoto and Eguchi, 2023 ; Ure, 1971 ; Halliday, 1985 ; Barkaoui and Hadidi, 2020 ; Zenker and Kyle, 2021 ; Kim et al. 2018 ; Lu, 2017 ; Ortega, 2015 ). Therefore, this study proposes five scoring categories: lexical richness, syntactic complexity, cohesion, content elaboration, and grammatical accuracy. A total of 16 measures were employed to capture these categories. The calculation process and specific details of these measures can be found in Table 2 .

T-unit, first introduced by Hunt ( 1966 ), is a measure used for evaluating speech and composition. It serves as an indicator of syntactic development and represents the shortest units into which a piece of discourse can be divided without leaving any sentence fragments. In the context of Japanese language assessment, Sakoda and Hosoi ( 2020 ) utilized T-unit as the basic unit to assess the accuracy and complexity of Japanese learners’ speaking and storytelling. The calculation of T-units in Japanese follows the following principles:

A single main clause constitutes 1 T-unit, regardless of the presence or absence of dependent clauses, e.g. (6).

ケンとマリはピクニックに行きました (main clause): 1 T-unit.

If a sentence contains a main clause along with subclauses, each subclause is considered part of the same T-unit, e.g. (7).

天気が良かった の で (subclause)、ケンとマリはピクニックに行きました (main clause): 1 T-unit.

In the case of coordinate clauses, where multiple clauses are connected, each coordinated clause is counted separately. Thus, a sentence with coordinate clauses may have 2 T-units or more, e.g. (8).

ケンは地図で場所を探して (coordinate clause)、マリはサンドイッチを作りました (coordinate clause): 2 T-units.

Lexical diversity refers to the range of words used within a text (Engber, 1995 ; Kyle et al. 2021 ) and is considered a useful measure of the breadth of vocabulary in L n production (Jarvis, 2013a , 2013b ).

The type/token ratio (TTR) is widely recognized as a straightforward measure for calculating lexical diversity and has been employed in numerous studies. These studies have demonstrated a strong correlation between TTR and other methods of measuring lexical diversity (e.g., Bentz et al. 2016 ; Čech and Miroslav, 2018 ; Çöltekin and Taraka, 2018 ). TTR is computed by considering both the number of unique words (types) and the total number of words (tokens) in a given text. Given that the length of learners’ writing texts can vary, this study employs the moving average type-token ratio (MATTR) to mitigate the influence of text length. MATTR is calculated using a 50-word moving window. Initially, a TTR is determined for words 1–50 in an essay, followed by words 2–51, 3–52, and so on until the end of the essay is reached (Díez-Ortega and Kyle, 2023 ). The final MATTR scores were obtained by averaging the TTR scores for all 50-word windows. The following formula was employed to derive MATTR:

\({\rm{MATTR}}({\rm{W}})=\frac{{\sum }_{{\rm{i}}=1}^{{\rm{N}}-{\rm{W}}+1}{{\rm{F}}}_{{\rm{i}}}}{{\rm{W}}({\rm{N}}-{\rm{W}}+1)}\)

Here, N refers to the number of tokens in the corpus. W is the randomly selected token size (W < N). \({F}_{i}\) is the number of types in each window. The \({\rm{MATTR}}({\rm{W}})\) is the mean of a series of type-token ratios (TTRs) based on the word form for all windows. It is expected that individuals with higher language proficiency will produce texts with greater lexical diversity, as indicated by higher MATTR scores.

Lexical density was captured by the ratio of the number of lexical words to the total number of words (Lu, 2012 ). Lexical sophistication refers to the utilization of advanced vocabulary, often evaluated through word frequency indices (Crossley et al. 2013 ; Haberman, 2008 ; Kyle and Crossley, 2015 ; Laufer and Nation, 1995 ; Lu, 2012 ; Read, 2000 ). In line of writing, lexical sophistication can be interpreted as vocabulary breadth, which entails the appropriate usage of vocabulary items across various lexicon-grammatical contexts and registers (Garner et al. 2019 ; Kim et al. 2018 ; Kyle et al. 2018 ). In Japanese specifically, words are considered lexically sophisticated if they are not included in the “Japanese Education Vocabulary List Ver 1.0”. Footnote 4 Consequently, lexical sophistication was calculated by determining the number of sophisticated word types relative to the total number of words per essay. Furthermore, it has been suggested that, in Japanese writing, sentences should ideally have a length of no more than 40 to 50 characters, as this promotes readability. Therefore, the median and maximum sentence length can be considered as useful indices for assessment (Ishioka and Kameda, 2006 ).

Syntactic complexity was assessed based on several measures, including the mean length of clauses, verb phrases per T-unit, clauses per T-unit, dependent clauses per T-unit, complex nominals per clause, adverbial clauses per clause, coordinate phrases per clause, and mean dependency distance (MDD). The MDD reflects the distance between the governor and dependent positions in a sentence. A larger dependency distance indicates a higher cognitive load and greater complexity in syntactic processing (Liu, 2008 ; Liu et al. 2017 ). The MDD has been established as an efficient metric for measuring syntactic complexity (Jiang, Quyang, and Liu, 2019 ; Li and Yan, 2021 ). To calculate the MDD, the position numbers of the governor and dependent are subtracted, assuming that words in a sentence are assigned in a linear order, such as W1 … Wi … Wn. In any dependency relationship between words Wa and Wb, Wa is the governor and Wb is the dependent. The MDD of the entire sentence was obtained by taking the absolute value of governor – dependent:

MDD = \(\frac{1}{n}{\sum }_{i=1}^{n}|{\rm{D}}{{\rm{D}}}_{i}|\)

In this formula, \(n\) represents the number of words in the sentence, and \({DD}i\) is the dependency distance of the \({i}^{{th}}\) dependency relationship of a sentence. Building on this, the annotation of sentence ‘Mary-ga-John-ni-keshigomu-o-watashita was [Mary- top -John- dat -eraser- acc -give- past] ’. The sentence’s MDD would be 2. Table 3 provides the CSV file as a prompt for GPT 4.

Cohesion (semantic similarity) and content elaboration aim to capture the ideas presented in test taker’s essays. Cohesion was assessed using three measures: Synonym overlap/paragraph (topic), Synonym overlap/paragraph (keywords), and word2vec cosine similarity. Content elaboration and development were measured as the number of metadiscourse markers (type)/number of words. To capture content closely, this study proposed a novel-distance based representation, by encoding the cosine distance between the essay (by learner) and essay task’s (topic and keyword) i -vectors. The learner’s essay is decoded into a word sequence, and aligned to the essay task’ topic and keyword for log-likelihood measurement. The cosine distance reveals the content elaboration score in the leaners’ essay. The mathematical equation of cosine similarity between target-reference vectors is shown in (11), assuming there are i essays and ( L i , …. L n ) and ( N i , …. N n ) are the vectors representing the learner and task’s topic and keyword respectively. The content elaboration distance between L i and N i was calculated as follows:

\(\cos \left(\theta \right)=\frac{{\rm{L}}\,\cdot\, {\rm{N}}}{\left|{\rm{L}}\right|{\rm{|N|}}}=\frac{\mathop{\sum }\nolimits_{i=1}^{n}{L}_{i}{N}_{i}}{\sqrt{\mathop{\sum }\nolimits_{i=1}^{n}{L}_{i}^{2}}\sqrt{\mathop{\sum }\nolimits_{i=1}^{n}{N}_{i}^{2}}}\)

A high similarity value indicates a low difference between the two recognition outcomes, which in turn suggests a high level of proficiency in content elaboration.

To evaluate the effectiveness of the proposed measures in distinguishing different proficiency levels among nonnative Japanese speakers’ writing, we conducted a multi-faceted Rasch measurement analysis (Linacre, 1994 ). This approach applies measurement models to thoroughly analyze various factors that can influence test outcomes, including test takers’ proficiency, item difficulty, and rater severity, among others. The underlying principles and functionality of multi-faceted Rasch measurement are illustrated in (12).

\(\log \left(\frac{{P}_{{nijk}}}{{P}_{{nij}(k-1)}}\right)={B}_{n}-{D}_{i}-{C}_{j}-{F}_{k}\)

(12) defines the logarithmic transformation of the probability ratio ( P nijk /P nij(k-1) )) as a function of multiple parameters. Here, n represents the test taker, i denotes a writing proficiency measure, j corresponds to the human rater, and k represents the proficiency score. The parameter B n signifies the proficiency level of test taker n (where n ranges from 1 to N). D j represents the difficulty parameter of test item i (where i ranges from 1 to L), while C j represents the severity of rater j (where j ranges from 1 to J). Additionally, F k represents the step difficulty for a test taker to move from score ‘k-1’ to k . P nijk refers to the probability of rater j assigning score k to test taker n for test item i . P nij(k-1) represents the likelihood of test taker n being assigned score ‘k-1’ by rater j for test item i . Each facet within the test is treated as an independent parameter and estimated within the same reference framework. To evaluate the consistency of scores obtained through both human and computer analysis, we utilized the Infit mean-square statistic. This statistic is a chi-square measure divided by the degrees of freedom and is weighted with information. It demonstrates higher sensitivity to unexpected patterns in responses to items near a person’s proficiency level (Linacre, 2002 ). Fit statistics are assessed based on predefined thresholds for acceptable fit. For the Infit MNSQ, which has a mean of 1.00, different thresholds have been suggested. Some propose stricter thresholds ranging from 0.7 to 1.3 (Bond et al. 2021 ), while others suggest more lenient thresholds ranging from 0.5 to 1.5 (Eckes, 2009 ). In this study, we adopted the criterion of 0.70–1.30 for the Infit MNSQ.

Moving forward, we can now proceed to assess the effectiveness of the 16 proposed measures based on five criteria for accurately distinguishing various levels of writing proficiency among non-native Japanese speakers. To conduct this evaluation, we utilized the development dataset from the I-JAS corpus, as described in Section Dataset . Table 4 provides a measurement report that presents the performance details of the 14 metrics under consideration. The measure separation was found to be 4.02, indicating a clear differentiation among the measures. The reliability index for the measure separation was 0.891, suggesting consistency in the measurement. Similarly, the person separation reliability index was 0.802, indicating the accuracy of the assessment in distinguishing between individuals. All 16 measures demonstrated Infit mean squares within a reasonable range, ranging from 0.76 to 1.28. The Synonym overlap/paragraph (topic) measure exhibited a relatively high outfit mean square of 1.46, although the Infit mean square falls within an acceptable range. The standard error for the measures ranged from 0.13 to 0.28, indicating the precision of the estimates.

Table 5 further illustrated the weights assigned to different linguistic measures for score prediction, with higher weights indicating stronger correlations between those measures and higher scores. Specifically, the following measures exhibited higher weights compared to others: moving average type token ratio per essay has a weight of 0.0391. Mean dependency distance had a weight of 0.0388. Mean length of clause, calculated by dividing the number of words by the number of clauses, had a weight of 0.0374. Complex nominals per T-unit, calculated by dividing the number of complex nominals by the number of T-units, had a weight of 0.0379. Coordinate phrases rate, calculated by dividing the number of coordinate phrases by the number of clauses, had a weight of 0.0325. Grammatical error rate, representing the number of errors per essay, had a weight of 0.0322.

Criteria (output indicator)

The criteria used to evaluate the writing ability in this study were based on CEFR, which follows a six-point scale ranging from A1 to C2. To assess the quality of Japanese writing, the scoring criteria from Table 6 were utilized. These criteria were derived from the IELTS writing standards and served as assessment guidelines and prompts for the written output.

A prompt is a question or detailed instruction that is provided to the model to obtain a proper response. After several pilot experiments, we decided to provide the measures (Section Measures of writing proficiency for nonnative Japanese ) as the input prompt and use the criteria (Section Criteria (output indicator) ) as the output indicator. Regarding the prompt language, considering that the LLM was tasked with rating Japanese essays, would prompt in Japanese works better Footnote 5 ? We conducted experiments comparing the performance of GPT-4 using both English and Japanese prompts. Additionally, we utilized the Japanese local model OCLL with Japanese prompts. Multiple trials were conducted using the same sample. Regardless of the prompt language used, we consistently obtained the same grading results with GPT-4, which assigned a grade of B1 to the writing sample. This suggested that GPT-4 is reliable and capable of producing consistent ratings regardless of the prompt language. On the other hand, when we used Japanese prompts with the Japanese local model “OCLL”, we encountered inconsistent grading results. Out of 10 attempts with OCLL, only 6 yielded consistent grading results (B1), while the remaining 4 showed different outcomes, including A1 and B2 grades. These findings indicated that the language of the prompt was not the determining factor for reliable AES. Instead, the size of the training data and the model parameters played crucial roles in achieving consistent and reliable AES results for the language model.

The following is the utilized prompt, which details all measures and requires the LLM to score the essays using holistic and trait scores.

Please evaluate Japanese essays written by Japanese learners and assign a score to each essay on a six-point scale, ranging from A1, A2, B1, B2, C1 to C2. Additionally, please provide trait scores and display the calculation process for each trait score. The scoring should be based on the following criteria:

Moving average type-token ratio.

Number of lexical words (token) divided by the total number of words per essay.

Number of sophisticated word types divided by the total number of words per essay.

Mean length of clause.

Verb phrases per T-unit.

Clauses per T-unit.

Dependent clauses per T-unit.

Complex nominals per clause.

Adverbial clauses per clause.

Coordinate phrases per clause.

Mean dependency distance.

Synonym overlap paragraph (topic and keywords).

Word2vec cosine similarity.

Connectives per essay.

Conjunctions per essay.

Number of metadiscourse markers (types) divided by the total number of words.

Number of errors per essay.

Japanese essay text

出かける前に二人が地図を見ている間に、サンドイッチを入れたバスケットに犬が入ってしまいました。それに気づかずに二人は楽しそうに出かけて行きました。やがて突然犬がバスケットから飛び出し、二人は驚きました。バスケット の 中を見ると、食べ物はすべて犬に食べられていて、二人は困ってしまいました。(ID_JJJ01_SW1)

The score of the example above was B1. Figure 3 provides an example of holistic and trait scores provided by GPT-4 (with a prompt indicating all measures) via Bing Footnote 6 .

Example of GPT-4 AES and feedback (with a prompt indicating all measures).

Statistical analysis

The aim of this study is to investigate the potential use of LLM for nonnative Japanese AES. It seeks to compare the scoring outcomes obtained from feature-based AES tools, which rely on conventional machine learning technology (i.e. Jess, JWriter), with those generated by AI-driven AES tools utilizing deep learning technology (BERT, GPT, OCLL). To assess the reliability of a computer-assisted annotation tool, the study initially established human-human agreement as the benchmark measure. Subsequently, the performance of the LLM-based method was evaluated by comparing it to human-human agreement.

To assess annotation agreement, the study employed standard measures such as precision, recall, and F-score (Brants 2000 ; Lu 2010 ), along with the quadratically weighted kappa (QWK) to evaluate the consistency and agreement in the annotation process. Assume A and B represent human annotators. When comparing the annotations of the two annotators, the following results are obtained. The evaluation of precision, recall, and F-score metrics was illustrated in equations (13) to (15).

\({\rm{Recall}}(A,B)=\frac{{\rm{Number}}\,{\rm{of}}\,{\rm{identical}}\,{\rm{nodes}}\,{\rm{in}}\,A\,{\rm{and}}\,B}{{\rm{Number}}\,{\rm{of}}\,{\rm{nodes}}\,{\rm{in}}\,A}\)

\({\rm{Precision}}(A,\,B)=\frac{{\rm{Number}}\,{\rm{of}}\,{\rm{identical}}\,{\rm{nodes}}\,{\rm{in}}\,A\,{\rm{and}}\,B}{{\rm{Number}}\,{\rm{of}}\,{\rm{nodes}}\,{\rm{in}}\,B}\)

The F-score is the harmonic mean of recall and precision:

\({\rm{F}}-{\rm{score}}=\frac{2* ({\rm{Precision}}* {\rm{Recall}})}{{\rm{Precision}}+{\rm{Recall}}}\)

The highest possible value of an F-score is 1.0, indicating perfect precision and recall, and the lowest possible value is 0, if either precision or recall are zero.

In accordance with Taghipour and Ng ( 2016 ), the calculation of QWK involves two steps:

Step 1: Construct a weight matrix W as follows:

\({W}_{{ij}}=\frac{{(i-j)}^{2}}{{(N-1)}^{2}}\)

i represents the annotation made by the tool, while j represents the annotation made by a human rater. N denotes the total number of possible annotations. Matrix O is subsequently computed, where O_( i, j ) represents the count of data annotated by the tool ( i ) and the human annotator ( j ). On the other hand, E refers to the expected count matrix, which undergoes normalization to ensure that the sum of elements in E matches the sum of elements in O.

Step 2: With matrices O and E, the QWK is obtained as follows:

K = 1- \(\frac{\sum i,j{W}_{i,j}\,{O}_{i,j}}{\sum i,j{W}_{i,j}\,{E}_{i,j}}\)

The value of the quadratic weighted kappa increases as the level of agreement improves. Further, to assess the accuracy of LLM scoring, the proportional reductive mean square error (PRMSE) was employed. The PRMSE approach takes into account the variability observed in human ratings to estimate the rater error, which is then subtracted from the variance of the human labels. This calculation provides an overall measure of agreement between the automated scores and true scores (Haberman et al. 2015 ; Loukina et al. 2020 ; Taghipour and Ng, 2016 ). The computation of PRMSE involves the following steps:

Step 1: Calculate the mean squared errors (MSEs) for the scoring outcomes of the computer-assisted tool (MSE tool) and the human scoring outcomes (MSE human).

Step 2: Determine the PRMSE by comparing the MSE of the computer-assisted tool (MSE tool) with the MSE from human raters (MSE human), using the following formula:

\({\rm{PRMSE}}=1-\frac{({\rm{MSE}}\,{\rm{tool}})\,}{({\rm{MSE}}\,{\rm{human}})\,}=1-\,\frac{{\sum }_{i}^{n}=1{({{\rm{y}}}_{i}-{\hat{{\rm{y}}}}_{{\rm{i}}})}^{2}}{{\sum }_{i}^{n}=1{({{\rm{y}}}_{i}-\hat{{\rm{y}}})}^{2}}\)

In the numerator, ŷi represents the scoring outcome predicted by a specific LLM-driven AES system for a given sample. The term y i − ŷ i represents the difference between this predicted outcome and the mean value of all LLM-driven AES systems’ scoring outcomes. It quantifies the deviation of the specific LLM-driven AES system’s prediction from the average prediction of all LLM-driven AES systems. In the denominator, y i − ŷ represents the difference between the scoring outcome provided by a specific human rater for a given sample and the mean value of all human raters’ scoring outcomes. It measures the discrepancy between the specific human rater’s score and the average score given by all human raters. The PRMSE is then calculated by subtracting the ratio of the MSE tool to the MSE human from 1. PRMSE falls within the range of 0 to 1, with larger values indicating reduced errors in LLM’s scoring compared to those of human raters. In other words, a higher PRMSE implies that LLM’s scoring demonstrates greater accuracy in predicting the true scores (Loukina et al. 2020 ). The interpretation of kappa values, ranging from 0 to 1, is based on the work of Landis and Koch ( 1977 ). Specifically, the following categories are assigned to different ranges of kappa values: −1 indicates complete inconsistency, 0 indicates random agreement, 0.0 ~ 0.20 indicates extremely low level of agreement (slight), 0.21 ~ 0.40 indicates moderate level of agreement (fair), 0.41 ~ 0.60 indicates medium level of agreement (moderate), 0.61 ~ 0.80 indicates high level of agreement (substantial), 0.81 ~ 1 indicates almost perfect level of agreement. All statistical analyses were executed using Python script.

Results and discussion

Annotation reliability of the llm.

This section focuses on assessing the reliability of the LLM’s annotation and scoring capabilities. To evaluate the reliability, several tests were conducted simultaneously, aiming to achieve the following objectives:

Assess the LLM’s ability to differentiate between test takers with varying levels of oral proficiency.

Determine the level of agreement between the annotations and scoring performed by the LLM and those done by human raters.

The evaluation of the results encompassed several metrics, including: precision, recall, F-Score, quadratically-weighted kappa, proportional reduction of mean squared error, Pearson correlation, and multi-faceted Rasch measurement.

Inter-annotator agreement (human–human annotator agreement)

We started with an agreement test of the two human annotators. Two trained annotators were recruited to determine the writing task data measures. A total of 714 scripts, as the test data, was utilized. Each analysis lasted 300–360 min. Inter-annotator agreement was evaluated using the standard measures of precision, recall, and F-score and QWK. Table 7 presents the inter-annotator agreement for the various indicators. As shown, the inter-annotator agreement was fairly high, with F-scores ranging from 1.0 for sentence and word number to 0.666 for grammatical errors.

The findings from the QWK analysis provided further confirmation of the inter-annotator agreement. The QWK values covered a range from 0.950 ( p  = 0.000) for sentence and word number to 0.695 for synonym overlap number (keyword) and grammatical errors ( p  = 0.001).

Agreement of annotation outcomes between human and LLM

To evaluate the consistency between human annotators and LLM annotators (BERT, GPT, OCLL) across the indices, the same test was conducted. The results of the inter-annotator agreement (F-score) between LLM and human annotation are provided in Appendix B-D. The F-scores ranged from 0.706 for Grammatical error # for OCLL-human to a perfect 1.000 for GPT-human, for sentences, clauses, T-units, and words. These findings were further supported by the QWK analysis, which showed agreement levels ranging from 0.807 ( p  = 0.001) for metadiscourse markers for OCLL-human to 0.962 for words ( p  = 0.000) for GPT-human. The findings demonstrated that the LLM annotation achieved a significant level of accuracy in identifying measurement units and counts.

Reliability of LLM-driven AES’s scoring and discriminating proficiency levels

This section examines the reliability of the LLM-driven AES scoring through a comparison of the scoring outcomes produced by human raters and the LLM ( Reliability of LLM-driven AES scoring ). It also assesses the effectiveness of the LLM-based AES system in differentiating participants with varying proficiency levels ( Reliability of LLM-driven AES discriminating proficiency levels ).

Reliability of LLM-driven AES scoring

Table 8 summarizes the QWK coefficient analysis between the scores computed by the human raters and the GPT-4 for the individual essays from I-JAS Footnote 7 . As shown, the QWK of all measures ranged from k  = 0.819 for lexical density (number of lexical words (tokens)/number of words per essay) to k  = 0.644 for word2vec cosine similarity. Table 9 further presents the Pearson correlations between the 16 writing proficiency measures scored by human raters and GPT 4 for the individual essays. The correlations ranged from 0.672 for syntactic complexity to 0.734 for grammatical accuracy. The correlations between the writing proficiency scores assigned by human raters and the BERT-based AES system were found to range from 0.661 for syntactic complexity to 0.713 for grammatical accuracy. The correlations between the writing proficiency scores given by human raters and the OCLL-based AES system ranged from 0.654 for cohesion to 0.721 for grammatical accuracy. These findings indicated an alignment between the assessments made by human raters and both the BERT-based and OCLL-based AES systems in terms of various aspects of writing proficiency.

Reliability of LLM-driven AES discriminating proficiency levels

After validating the reliability of the LLM’s annotation and scoring, the subsequent objective was to evaluate its ability to distinguish between various proficiency levels. For this analysis, a dataset of 686 individual essays was utilized. Table 10 presents a sample of the results, summarizing the means, standard deviations, and the outcomes of the one-way ANOVAs based on the measures assessed by the GPT-4 model. A post hoc multiple comparison test, specifically the Bonferroni test, was conducted to identify any potential differences between pairs of levels.

As the results reveal, seven measures presented linear upward or downward progress across the three proficiency levels. These were marked in bold in Table 10 and comprise one measure of lexical richness, i.e. MATTR (lexical diversity); four measures of syntactic complexity, i.e. MDD (mean dependency distance), MLC (mean length of clause), CNT (complex nominals per T-unit), CPC (coordinate phrases rate); one cohesion measure, i.e. word2vec cosine similarity and GER (grammatical error rate). Regarding the ability of the sixteen measures to distinguish adjacent proficiency levels, the Bonferroni tests indicated that statistically significant differences exist between the primary level and the intermediate level for MLC and GER. One measure of lexical richness, namely LD, along with three measures of syntactic complexity (VPT, CT, DCT, ACC), two measures of cohesion (SOPT, SOPK), and one measure of content elaboration (IMM), exhibited statistically significant differences between proficiency levels. However, these differences did not demonstrate a linear progression between adjacent proficiency levels. No significant difference was observed in lexical sophistication between proficiency levels.

To summarize, our study aimed to evaluate the reliability and differentiation capabilities of the LLM-driven AES method. For the first objective, we assessed the LLM’s ability to differentiate between test takers with varying levels of oral proficiency using precision, recall, F-Score, and quadratically-weighted kappa. Regarding the second objective, we compared the scoring outcomes generated by human raters and the LLM to determine the level of agreement. We employed quadratically-weighted kappa and Pearson correlations to compare the 16 writing proficiency measures for the individual essays. The results confirmed the feasibility of using the LLM for annotation and scoring in AES for nonnative Japanese. As a result, Research Question 1 has been addressed.

Comparison of BERT-, GPT-, OCLL-based AES, and linguistic-feature-based computation methods

This section aims to compare the effectiveness of five AES methods for nonnative Japanese writing, i.e. LLM-driven approaches utilizing BERT, GPT, and OCLL, linguistic feature-based approaches using Jess and JWriter. The comparison was conducted by comparing the ratings obtained from each approach with human ratings. All ratings were derived from the dataset introduced in Dataset . To facilitate the comparison, the agreement between the automated methods and human ratings was assessed using QWK and PRMSE. The performance of each approach was summarized in Table 11 .

The QWK coefficient values indicate that LLMs (GPT, BERT, OCLL) and human rating outcomes demonstrated higher agreement compared to feature-based AES methods (Jess and JWriter) in assessing writing proficiency criteria, including lexical richness, syntactic complexity, content, and grammatical accuracy. Among the LLMs, the GPT-4 driven AES and human rating outcomes showed the highest agreement in all criteria, except for syntactic complexity. The PRMSE values suggest that the GPT-based method outperformed linguistic feature-based methods and other LLM-based approaches. Moreover, an interesting finding emerged during the study: the agreement coefficient between GPT-4 and human scoring was even higher than the agreement between different human raters themselves. This discovery highlights the advantage of GPT-based AES over human rating. Ratings involve a series of processes, including reading the learners’ writing, evaluating the content and language, and assigning scores. Within this chain of processes, various biases can be introduced, stemming from factors such as rater biases, test design, and rating scales. These biases can impact the consistency and objectivity of human ratings. GPT-based AES may benefit from its ability to apply consistent and objective evaluation criteria. By prompting the GPT model with detailed writing scoring rubrics and linguistic features, potential biases in human ratings can be mitigated. The model follows a predefined set of guidelines and does not possess the same subjective biases that human raters may exhibit. This standardization in the evaluation process contributes to the higher agreement observed between GPT-4 and human scoring. Section Prompt strategy of the study delves further into the role of prompts in the application of LLMs to AES. It explores how the choice and implementation of prompts can impact the performance and reliability of LLM-based AES methods. Furthermore, it is important to acknowledge the strengths of the local model, i.e. the Japanese local model OCLL, which excels in processing certain idiomatic expressions. Nevertheless, our analysis indicated that GPT-4 surpasses local models in AES. This superior performance can be attributed to the larger parameter size of GPT-4, estimated to be between 500 billion and 1 trillion, which exceeds the sizes of both BERT and the local model OCLL.

Prompt strategy

In the context of prompt strategy, Mizumoto and Eguchi ( 2023 ) conducted a study where they applied the GPT-3 model to automatically score English essays in the TOEFL test. They found that the accuracy of the GPT model alone was moderate to fair. However, when they incorporated linguistic measures such as cohesion, syntactic complexity, and lexical features alongside the GPT model, the accuracy significantly improved. This highlights the importance of prompt engineering and providing the model with specific instructions to enhance its performance. In this study, a similar approach was taken to optimize the performance of LLMs. GPT-4, which outperformed BERT and OCLL, was selected as the candidate model. Model 1 was used as the baseline, representing GPT-4 without any additional prompting. Model 2, on the other hand, involved GPT-4 prompted with 16 measures that included scoring criteria, efficient linguistic features for writing assessment, and detailed measurement units and calculation formulas. The remaining models (Models 3 to 18) utilized GPT-4 prompted with individual measures. The performance of these 18 different models was assessed using the output indicators described in Section Criteria (output indicator) . By comparing the performances of these models, the study aimed to understand the impact of prompt engineering on the accuracy and effectiveness of GPT-4 in AES tasks.

Based on the PRMSE scores presented in Fig. 4 , it was observed that Model 1, representing GPT-4 without any additional prompting, achieved a fair level of performance. However, Model 2, which utilized GPT-4 prompted with all measures, outperformed all other models in terms of PRMSE score, achieving a score of 0.681. These results indicate that the inclusion of specific measures and prompts significantly enhanced the performance of GPT-4 in AES. Among the measures, syntactic complexity was found to play a particularly significant role in improving the accuracy of GPT-4 in assessing writing quality. Following that, lexical diversity emerged as another important factor contributing to the model’s effectiveness. The study suggests that a well-prompted GPT-4 can serve as a valuable tool to support human assessors in evaluating writing quality. By utilizing GPT-4 as an automated scoring tool, the evaluation biases associated with human raters can be minimized. This has the potential to empower teachers by allowing them to focus on designing writing tasks and guiding writing strategies, while leveraging the capabilities of GPT-4 for efficient and reliable scoring.

PRMSE scores of the 18 AES models.

This study aimed to investigate two main research questions: the feasibility of utilizing LLMs for AES and the impact of prompt engineering on the application of LLMs in AES.

To address the first objective, the study compared the effectiveness of five different models: GPT, BERT, the Japanese local LLM (OCLL), and two conventional machine learning-based AES tools (Jess and JWriter). The PRMSE values indicated that the GPT-4-based method outperformed other LLMs (BERT, OCLL) and linguistic feature-based computational methods (Jess and JWriter) across various writing proficiency criteria. Furthermore, the agreement coefficient between GPT-4 and human scoring surpassed the agreement among human raters themselves, highlighting the potential of using the GPT-4 tool to enhance AES by reducing biases and subjectivity, saving time, labor, and cost, and providing valuable feedback for self-study. Regarding the second goal, the role of prompt design was investigated by comparing 18 models, including a baseline model, a model prompted with all measures, and 16 models prompted with one measure at a time. GPT-4, which outperformed BERT and OCLL, was selected as the candidate model. The PRMSE scores of the models showed that GPT-4 prompted with all measures achieved the best performance, surpassing the baseline and other models.

In conclusion, this study has demonstrated the potential of LLMs in supporting human rating in assessments. By incorporating automation, we can save time and resources while reducing biases and subjectivity inherent in human rating processes. Automated language assessments offer the advantage of accessibility, providing equal opportunities and economic feasibility for individuals who lack access to traditional assessment centers or necessary resources. LLM-based language assessments provide valuable feedback and support to learners, aiding in the enhancement of their language proficiency and the achievement of their goals. This personalized feedback can cater to individual learner needs, facilitating a more tailored and effective language-learning experience.

There are three important areas that merit further exploration. First, prompt engineering requires attention to ensure optimal performance of LLM-based AES across different language types. This study revealed that GPT-4, when prompted with all measures, outperformed models prompted with fewer measures. Therefore, investigating and refining prompt strategies can enhance the effectiveness of LLMs in automated language assessments. Second, it is crucial to explore the application of LLMs in second-language assessment and learning for oral proficiency, as well as their potential in under-resourced languages. Recent advancements in self-supervised machine learning techniques have significantly improved automatic speech recognition (ASR) systems, opening up new possibilities for creating reliable ASR systems, particularly for under-resourced languages with limited data. However, challenges persist in the field of ASR. First, ASR assumes correct word pronunciation for automatic pronunciation evaluation, which proves challenging for learners in the early stages of language acquisition due to diverse accents influenced by their native languages. Accurately segmenting short words becomes problematic in such cases. Second, developing precise audio-text transcriptions for languages with non-native accented speech poses a formidable task. Last, assessing oral proficiency levels involves capturing various linguistic features, including fluency, pronunciation, accuracy, and complexity, which are not easily captured by current NLP technology.

Data availability

The dataset utilized was obtained from the International Corpus of Japanese as a Second Language (I-JAS). The data URLs: [ https://www2.ninjal.ac.jp/jll/lsaj/ihome2.html ].

J-CAT and TTBJ are two computerized adaptive tests used to assess Japanese language proficiency.

SPOT is a specific component of the TTBJ test.

J-CAT: https://www.j-cat2.org/html/ja/pages/interpret.html

SPOT: https://ttbj.cegloc.tsukuba.ac.jp/p1.html#SPOT .

The study utilized a prompt-based GPT-4 model, developed by OpenAI, which has an impressive architecture with 1.8 trillion parameters across 120 layers. GPT-4 was trained on a vast dataset of 13 trillion tokens, using two stages: initial training on internet text datasets to predict the next token, and subsequent fine-tuning through reinforcement learning from human feedback.

https://www2.ninjal.ac.jp/jll/lsaj/ihome2-en.html .

http://jhlee.sakura.ne.jp/JEV/ by Japanese Learning Dictionary Support Group 2015.

We express our sincere gratitude to the reviewer for bringing this matter to our attention.

On February 7, 2023, Microsoft began rolling out a major overhaul to Bing that included a new chatbot feature based on OpenAI’s GPT-4 (Bing.com).

Appendix E-F present the analysis results of the QWK coefficient between the scores computed by the human raters and the BERT, OCLL models.

Attali Y, Burstein J (2006) Automated essay scoring with e-rater® V.2. J. Technol., Learn. Assess., 4

Barkaoui K, Hadidi A (2020) Assessing Change in English Second Language Writing Performance (1st ed.). Routledge, New York. https://doi.org/10.4324/9781003092346

Bentz C, Tatyana R, Koplenig A, Tanja S (2016) A comparison between morphological complexity. measures: Typological data vs. language corpora. In Proceedings of the workshop on computational linguistics for linguistic complexity (CL4LC), 142–153. Osaka, Japan: The COLING 2016 Organizing Committee

Bond TG, Yan Z, Heene M (2021) Applying the Rasch model: Fundamental measurement in the human sciences (4th ed). Routledge

Brants T (2000) Inter-annotator agreement for a German newspaper corpus. Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00), Athens, Greece, 31 May-2 June, European Language Resources Association

Brown TB, Mann B, Ryder N, et al. (2020) Language models are few-shot learners. Advances in Neural Information Processing Systems, Online, 6–12 December, Curran Associates, Inc., Red Hook, NY

Burstein J (2003) The E-rater scoring engine: Automated essay scoring with natural language processing. In Shermis MD and Burstein JC (ed) Automated Essay Scoring: A Cross-Disciplinary Perspective. Lawrence Erlbaum Associates, Mahwah, NJ

Čech R, Miroslav K (2018) Morphological richness of text. In Masako F, Václav C (ed) Taming the corpus: From inflection and lexis to interpretation, 63–77. Cham, Switzerland: Springer Nature

Çöltekin Ç, Taraka, R (2018) Exploiting Universal Dependencies treebanks for measuring morphosyntactic complexity. In Aleksandrs B, Christian B (ed), Proceedings of first workshop on measuring language complexity, 1–7. Torun, Poland

Crossley SA, Cobb T, McNamara DS (2013) Comparing count-based and band-based indices of word frequency: Implications for active vocabulary research and pedagogical applications. System 41:965–981. https://doi.org/10.1016/j.system.2013.08.002

Article   Google Scholar  

Crossley SA, McNamara DS (2016) Say more and be more coherent: How text elaboration and cohesion can increase writing quality. J. Writ. Res. 7:351–370

CyberAgent Inc (2023) Open-Calm series of Japanese language models. Retrieved from: https://www.cyberagent.co.jp/news/detail/id=28817

Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, Minnesota, 2–7 June, pp. 4171–4186. Association for Computational Linguistics

Diez-Ortega M, Kyle K (2023) Measuring the development of lexical richness of L2 Spanish: a longitudinal learner corpus study. Studies in Second Language Acquisition 1-31

Eckes T (2009) On common ground? How raters perceive scoring criteria in oral proficiency testing. In Brown A, Hill K (ed) Language testing and evaluation 13: Tasks and criteria in performance assessment (pp. 43–73). Peter Lang Publishing

Elliot S (2003) IntelliMetric: from here to validity. In: Shermis MD, Burstein JC (ed) Automated Essay Scoring: A Cross-Disciplinary Perspective. Lawrence Erlbaum Associates, Mahwah, NJ

Google Scholar  

Engber CA (1995) The relationship of lexical proficiency to the quality of ESL compositions. J. Second Lang. Writ. 4:139–155

Garner J, Crossley SA, Kyle K (2019) N-gram measures and L2 writing proficiency. System 80:176–187. https://doi.org/10.1016/j.system.2018.12.001

Haberman SJ (2008) When can subscores have value? J. Educat. Behav. Stat., 33:204–229

Haberman SJ, Yao L, Sinharay S (2015) Prediction of true test scores from observed item scores and ancillary data. Brit. J. Math. Stat. Psychol. 68:363–385

Halliday MAK (1985) Spoken and Written Language. Deakin University Press, Melbourne, Australia

Hirao R, Arai M, Shimanaka H et al. (2020) Automated essay scoring system for nonnative Japanese learners. Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pp. 1250–1257. European Language Resources Association

Hunt KW (1966) Recent Measures in Syntactic Development. Elementary English, 43(7), 732–739. http://www.jstor.org/stable/41386067

Ishioka T (2001) About e-rater, a computer-based automatic scoring system for essays [Konpyūta ni yoru essei no jidō saiten shisutemu e − rater ni tsuite]. University Entrance Examination. Forum [Daigaku nyūshi fōramu] 24:71–76

Hochreiter S, Schmidhuber J (1997) Long short- term memory. Neural Comput. 9(8):1735–1780

Article   CAS   PubMed   Google Scholar  

Ishioka T, Kameda M (2006) Automated Japanese essay scoring system based on articles written by experts. Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, 17–18 July 2006, pp. 233-240. Association for Computational Linguistics, USA

Japan Foundation (2021) Retrieved from: https://www.jpf.gp.jp/j/project/japanese/survey/result/dl/survey2021/all.pdf

Jarvis S (2013a) Defining and measuring lexical diversity. In Jarvis S, Daller M (ed) Vocabulary knowledge: Human ratings and automated measures (Vol. 47, pp. 13–44). John Benjamins. https://doi.org/10.1075/sibil.47.03ch1

Jarvis S (2013b) Capturing the diversity in lexical diversity. Lang. Learn. 63:87–106. https://doi.org/10.1111/j.1467-9922.2012.00739.x

Jiang J, Quyang J, Liu H (2019) Interlanguage: A perspective of quantitative linguistic typology. Lang. Sci. 74:85–97

Kim M, Crossley SA, Kyle K (2018) Lexical sophistication as a multidimensional phenomenon: Relations to second language lexical proficiency, development, and writing quality. Mod. Lang. J. 102(1):120–141. https://doi.org/10.1111/modl.12447

Kojima T, Gu S, Reid M et al. (2022) Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems, New Orleans, LA, 29 November-1 December, Curran Associates, Inc., Red Hook, NY

Kyle K, Crossley SA (2015) Automatically assessing lexical sophistication: Indices, tools, findings, and application. TESOL Q 49:757–786

Kyle K, Crossley SA, Berger CM (2018) The tool for the automatic analysis of lexical sophistication (TAALES): Version 2.0. Behav. Res. Methods 50:1030–1046. https://doi.org/10.3758/s13428-017-0924-4

Article   PubMed   Google Scholar  

Kyle K, Crossley SA, Jarvis S (2021) Assessing the validity of lexical diversity using direct judgements. Lang. Assess. Q. 18:154–170. https://doi.org/10.1080/15434303.2020.1844205

Landauer TK, Laham D, Foltz PW (2003) Automated essay scoring and annotation of essays with the Intelligent Essay Assessor. In Shermis MD, Burstein JC (ed), Automated Essay Scoring: A Cross-Disciplinary Perspective. Lawrence Erlbaum Associates, Mahwah, NJ

Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 159–174

Laufer B, Nation P (1995) Vocabulary size and use: Lexical richness in L2 written production. Appl. Linguist. 16:307–322. https://doi.org/10.1093/applin/16.3.307

Lee J, Hasebe Y (2017) jWriter Learner Text Evaluator, URL: https://jreadability.net/jwriter/

Lee J, Kobayashi N, Sakai T, Sakota K (2015) A Comparison of SPOT and J-CAT Based on Test Analysis [Tesuto bunseki ni motozuku ‘SPOT’ to ‘J-CAT’ no hikaku]. Research on the Acquisition of Second Language Japanese [Dainigengo to shite no nihongo no shūtoku kenkyū] (18) 53–69

Li W, Yan J (2021) Probability distribution of dependency distance based on a Treebank of. Japanese EFL Learners’ Interlanguage. J. Quant. Linguist. 28(2):172–186. https://doi.org/10.1080/09296174.2020.1754611

Article   MathSciNet   Google Scholar  

Linacre JM (2002) Optimizing rating scale category effectiveness. J. Appl. Meas. 3(1):85–106

PubMed   Google Scholar  

Linacre JM (1994) Constructing measurement with a Many-Facet Rasch Model. In Wilson M (ed) Objective measurement: Theory into practice, Volume 2 (pp. 129–144). Norwood, NJ: Ablex

Liu H (2008) Dependency distance as a metric of language comprehension difficulty. J. Cognitive Sci. 9:159–191

Liu H, Xu C, Liang J (2017) Dependency distance: A new perspective on syntactic patterns in natural languages. Phys. Life Rev. 21. https://doi.org/10.1016/j.plrev.2017.03.002

Loukina A, Madnani N, Cahill A, et al. (2020) Using PRMSE to evaluate automated scoring systems in the presence of label noise. Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, Seattle, WA, USA → Online, 10 July, pp. 18–29. Association for Computational Linguistics

Lu X (2010) Automatic analysis of syntactic complexity in second language writing. Int. J. Corpus Linguist. 15:474–496

Lu X (2012) The relationship of lexical richness to the quality of ESL learners’ oral narratives. Mod. Lang. J. 96:190–208

Lu X (2017) Automated measurement of syntactic complexity in corpus-based L2 writing research and implications for writing assessment. Lang. Test. 34:493–511

Lu X, Hu R (2022) Sense-aware lexical sophistication indices and their relationship to second language writing quality. Behav. Res. Method. 54:1444–1460. https://doi.org/10.3758/s13428-021-01675-6

Ministry of Health, Labor, and Welfare of Japan (2022) Retrieved from: https://www.mhlw.go.jp/stf/newpage_30367.html

Mizumoto A, Eguchi M (2023) Exploring the potential of using an AI language model for automated essay scoring. Res. Methods Appl. Linguist. 3:100050

Okgetheng B, Takeuchi K (2024) Estimating Japanese Essay Grading Scores with Large Language Models. Proceedings of 30th Annual Conference of the Language Processing Society in Japan, March 2024

Ortega L (2015) Second language learning explained? SLA across 10 contemporary theories. In VanPatten B, Williams J (ed) Theories in Second Language Acquisition: An Introduction

Rae JW, Borgeaud S, Cai T, et al. (2021) Scaling Language Models: Methods, Analysis & Insights from Training Gopher. ArXiv, abs/2112.11446

Read J (2000) Assessing vocabulary. Cambridge University Press. https://doi.org/10.1017/CBO9780511732942

Rudner LM, Liang T (2002) Automated Essay Scoring Using Bayes’ Theorem. J. Technol., Learning and Assessment, 1 (2)

Sakoda K, Hosoi Y (2020) Accuracy and complexity of Japanese Language usage by SLA learners in different learning environments based on the analysis of I-JAS, a learners’ corpus of Japanese as L2. Math. Linguist. 32(7):403–418. https://doi.org/10.24701/mathling.32.7_403

Suzuki N (1999) Summary of survey results regarding comprehensive essay questions. Final report of “Joint Research on Comprehensive Examinations for the Aim of Evaluating Applicability to Each Specialized Field of Universities” for 1996-2000 [shōronbun sōgō mondai ni kansuru chōsa kekka no gaiyō. Heisei 8 - Heisei 12-nendo daigaku no kaku senmon bun’ya e no tekisei no hyōka o mokuteki to suru sōgō shiken no arikata ni kansuru kyōdō kenkyū’ saishū hōkoku-sho]. University Entrance Examination Section Center Research and Development Department [Daigaku nyūshi sentā kenkyū kaihatsubu], 21–32

Taghipour K, Ng HT (2016) A neural approach to automated essay scoring. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, 1–5 November, pp. 1882–1891. Association for Computational Linguistics

Takeuchi K, Ohno M, Motojin K, Taguchi M, Inada Y, Iizuka M, Abo T, Ueda H (2021) Development of essay scoring methods based on reference texts with construction of research-available Japanese essay data. In IPSJ J 62(9):1586–1604

Ure J (1971) Lexical density: A computational technique and some findings. In Coultard M (ed) Talking about Text. English Language Research, University of Birmingham, Birmingham, England

Vaswani A, Shazeer N, Parmar N, et al. (2017) Attention is all you need. In Advances in Neural Information Processing Systems, Long Beach, CA, 4–7 December, pp. 5998–6008, Curran Associates, Inc., Red Hook, NY

Watanabe H, Taira Y, Inoue Y (1988) Analysis of essay evaluation data [Shōronbun hyōka dēta no kaiseki]. Bulletin of the Faculty of Education, University of Tokyo [Tōkyōdaigaku kyōiku gakubu kiyō], Vol. 28, 143–164

Yao S, Yu D, Zhao J, et al. (2023) Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36

Zenker F, Kyle K (2021) Investigating minimum text lengths for lexical diversity indices. Assess. Writ. 47:100505. https://doi.org/10.1016/j.asw.2020.100505

Zhang Y, Warstadt A, Li X, et al. (2021) When do you need billions of words of pretraining data? Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Online, pp. 1112-1125. Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.acl-long.90

Download references

This research was funded by National Foundation of Social Sciences (22BYY186) to Wenchao Li.

Author information

Authors and affiliations.

Department of Japanese Studies, Zhejiang University, Hangzhou, China

Department of Linguistics and Applied Linguistics, Zhejiang University, Hangzhou, China

You can also search for this author in PubMed   Google Scholar

Contributions

Wenchao Li is in charge of conceptualization, validation, formal analysis, investigation, data curation, visualization and writing the draft. Haitao Liu is in charge of supervision.

Corresponding author

Correspondence to Wenchao Li .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Ethical approval

Ethical approval was not required as the study did not involve human participants.

Informed consent

This article does not contain any studies with human participants performed by any of the authors.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplemental material file #1, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Li, W., Liu, H. Applying large language models for automated essay scoring for non-native Japanese. Humanit Soc Sci Commun 11 , 723 (2024). https://doi.org/10.1057/s41599-024-03209-9

Download citation

Received : 02 February 2024

Accepted : 16 May 2024

Published : 03 June 2024

DOI : https://doi.org/10.1057/s41599-024-03209-9

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies