People are still figuring out the best use cases for ChatGPT, the popular chatbot based on a powerful AI language model. This article provides some ideas for how to use the tool to assist with your academic writing.
ChatGPT can assist you with the following steps when writing a paper, thesis, or dissertation:
Developing a research question with ChatGPT
You can use ChatGPT to help you formulate a clear and concise research question by generating and improving potential questions.
With the help of ChatGPT, you can develop a large number of possible research questions within a short time. This is a great way to generate ideas and different approaches to a topic.
However, make sure that the generated questions make sense and meet your needs. As you can see from our example, you can keep working with ChatGPT to adapt its suggestions to your needs (or just edit the text directly if you already have a clear idea of what you want).
First input
Develop three possible research questions on the following topic: “The influence of social media on political opinion formation.”
ChatGPT output
- To what extent does exposure to diverse political perspectives on social media affect individuals’ political opinions and behaviors?
- How does the personalized algorithm of social media platforms shape the formation of political opinions among its users?
- What are the underlying factors that determine the effect of social media on political opinion formation, and how can they be measured and analyzed?
Second input
Based on the second research question, develop three further research questions on the topic of polarization in US politics.
- Build my scientific method, qualitative discourse analysis, into each question
- Include the term “filter bubble” in each question
ChatGPT output
- How does the filter bubble effect on social media platforms contribute to the polarization of political attitudes in the US? A qualitative discourse analysis.
- What is the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US? A qualitative discourse analysis.
- How does the influence of filter bubbles on social media affect the ability of individuals to engage in productive political discourse across ideological divides in the US? A qualitative discourse analysis.
Third input
Try to incorporate “qualitative discourse analysis” into the questions themselves, instead of using it as a separate sentence.
ChatGPT output
- How does a qualitative discourse analysis of filter bubble effect on social media platforms contribute to understanding the polarization of political attitudes in the US?
- What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?
- How does a qualitative discourse analysis of the influence of filter bubbles on social media inform our understanding of the ability of individuals to engage in productive political discourse across ideological divides in the US?
Creating an outline of your paper with ChatGPT
You can also use ChatGPT to help you draft a research paper outline or thesis outline. To do this, try generating possible headings and subheadings and then improving them. ChatGPT can help to generate a clear and well-structured outline, especially if you keep adjusting the structure with its help.
However, it doesn’t have a deep understanding of your topic. As a result, inappropriate headings may sometimes be generated. It’s important to check that the outline makes sense and covers all the points needed to answer your research question.
You should also ensure that the headings and subheadings follow a logical structure. Scribbr’s Proofreading & Editing service can help you with this.
First input
Create an outline for an academic research paper with the following research question:
“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?”
The paper will be about 8 pages long.
ChatGPT output
- Introduction
-
- Background information on filter bubbles and political echo chambers
- Purpose of the study
- Research question
- Thesis statement
-
- Literature Review
-
- Definition and concept of filter bubbles
- Definition and concept of political echo chambers
- Previous studies on the role of filter bubbles in perpetuating and reinforcing political echo chambers
- Critiques and limitations of previous studies
-
- Methodology
-
- Research design
- Participants
- Data collection and analysis
- Validity and reliability
-
- Results
-
- Findings from qualitative discourse analysis
- Results related to the research question
- Implications of the findings
-
- Discussion
-
- Interpretation of the results
- Comparison with previous studies
- Limitations of the study
- Implications for future research
-
- Conclusion
-
- Summary of the results
- Implications for understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers
- Conclusion and recommendations for future research
-
- References
-
- List of references used in the paper
-
- Appendices
-
- Data collection materials
- Examples of qualitative data analysis
-
Second input
This seems like too much information to fit into only 8 pages. Can you condense the outline, for example removing the appendices and simplifying the structure?
ChatGPT output
- Introduction
-
- Background on filter bubbles and political echo chambers
- Purpose of the study
- Research question
- Thesis statement
-
- Literature Review
-
- Definition of filter bubbles and political echo chambers
- Previous studies on the role of filter bubbles
- Limitations of previous studies
-
- Methodology
-
- Research design
- Participants
- Data collection and analysis
-
- Results
-
- Findings from qualitative discourse analysis
- Results related to the research question
- Implications of the findings
-
- Discussion
-
- Interpretation of the results
- Limitations of the study
- Implications for future research
-
- Conclusion
-
- Summary of the results
- Implications for understanding the role of filter bubbles
- Final thoughts
-
- References
-
- List of references used in the paper
-
Generate literature ideas
ChatGPT can be a useful way to generate ideas regarding what sources you might use in your work. Try asking it for suggestions about where to look and what to consider.
However, we advise against using it to find sources directly. It’s not designed for this and, if asked to do it, often just creates fake sources and presents them as real. Search a database like Google Scholar instead.
First input
What types of sources could I use to write a paper on the following research question?
“What is the contribution of a qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US?”
ChatGPT output
When writing a paper on the contribution of qualitative discourse analysis to understanding the role of filter bubbles in perpetuating and reinforcing political echo chambers in the US, you could use the following types of sources:
- Academic journals and articles: These are a good place to start when you’re looking for information on specific topics and they can provide you with in-depth analysis and perspectives on the topic at hand.
- Books and book chapters: These sources can provide comprehensive overviews of a particular topic and can also offer theoretical frameworks and historical perspectives.
- Government reports and studies: Government agencies, such as the Federal Communications Commission (FCC), may have conducted studies on the role of filter bubbles in perpetuating political echo chambers.
- News articles and media reports: These sources can provide insight into the current state of the issue, as well as opinions from various stakeholders.
- Online sources: Websites, blogs, and online forums can provide a range of perspectives on the topic and can also be useful in exploring the experiences of individuals who are affected by filter bubbles and political echo chambers.
- Data and statistics: Relevant data and statistics on the prevalence and impact of filter bubbles and political echo chambers in the US can be useful in providing evidence to support your arguments.
- Expert interviews and focus groups: Conducting expert interviews or focus groups with individuals who have experience with or knowledge of the topic can provide valuable insights and perspectives that can be used to support your arguments.
Paraphrasing text
You can also try using ChatGPT to paraphrase text. ChatGPT can quickly generate a number of different paraphrases of the same idea. You can keep typing “again” in the chat until you are satisfied with the result.
This kind of paraphrasing can be helpful to, for example, non-native speakers who want to improve the fluency of their text. However, be careful. The paraphrases often:
- Contain grammatical errors
- Include false information
So you should always check the output to make sure it’s correct. If you’re unsure, you can run the text through the Scribbr Grammar Checker and cross-reference the information against other, more credible sources.
An alternative is to use the Scribbr Paraphrasing Tool, which was designed directly for this purpose.
Input
Paraphrase the following text:
“A filter bubble results from a social media algorithm’s attempts to cater to an individual user based on data such as their search history and previous behavior on the site. It results in the user only being presented with information that confirms their biases.”
Restructure the sentences and use other phrasings for the following parts:
- “results from”
- “only being presented with”
ChatGPT output
“A filter bubble is created when a social media algorithm customizes its content for a particular user based on their data, such as their search history and past actions on the platform. This leads to the user being confined to information that reinforces their pre-existing beliefs.”
ChatGPT sometimes doesn’t generate original text, instead adopting phrasings from existing texts. This will be recognized by your university’s plagiarism checker. And more specialized AI writing detectors are already starting to appear.
Getting feedback from ChatGPT
You can also use ChatGPT to get feedback on the argumentation and structure of your paper and suggestions for improvements.
An advantage of this is that you can get feedback from ChatGPT on different text excerpts at any time. However, one downside is that ChatGPT does not have a deep understanding of your research question, so its feedback and suggestions may be shallow or inappropriate.
This kind of feedback cannot replace input from an experienced academic supervisor who’s familiar with your topic. Use ChatGPT feedback as a supplement, not a substitute for human feedback.
If you need in-depth feedback on your writing from someone with academic expertise, try Scribbr’s Proofreading & Editing service.
Behave like a scientific supervisor in their office hours. You must review and critically assess the current state of this section of my research paper. To do this, evaluate the clarity of my explanations, the smoothness of the language, and the way I’ve structured the text, giving constructive criticism on each issue:
[Text you want to get feedback on.]
ChatGPT output
Thank you for submitting your research paper for review. Let me provide you with my constructive criticism:
Clarity of Explanations: Overall, the explanations are clear and concise, but there are a few areas that could benefit from additional clarification. For example, in the first paragraph, you mention “the mental lexicon,” but do not provide a definition or further explanation for what this is. It would also be helpful to provide a definition of “lemma.”
Smoothness of Language: The language in the paper is generally smooth, but there are a few instances where it could be refined. For example, the sentence “The symptoms vary from adding superfluous words and taking pauses to hoarseness of the voice” could be rephrased to “The symptoms of these disorders can range from excessive use of words and pauses to hoarseness.”
Structure of Text: The structure of the text is clear, with each paragraph building on the previous one. However, the transition between the first two paragraphs could be smoother. Perhaps you could add a sentence or two to bridge the gap between the two topics.
In conclusion, your paper is well-written, but there are a few areas where it could benefit from some refinement. Keep up the good work! If you have any questions or would like to discuss my comments further, please let me know.
Limitations of ChatGPT
Even though ChatGPT is a powerful writing tool, you should keep the following limitations in mind:
No original research
ChatGPT was trained using existing texts, and the texts created by the AI are based on this data. It’s not capable of doing its own research, only of synthesizing sources that it was trained on.
Additionally, because the texts that it was trained on only go up to 2021, it’s unfamiliar with more recent world events, cultural trends, and developments in different fields of research. This means it may provide outdated information.
Risk of plagiarism
Because ChatGPT was trained using existing text, the AI tends to reuse that content in a way that may be considered plagiarism. The AI may copy text from an online publication in its responses.
Additionally, using ChatGPT to write your assignment for you is considered plagiarism regardless of where it got the content from, because you’re passing off something you didn’t write as your own work.
Fake sources
ChatGPT was trained on a wide variety of sources, but it’s not able to accurately tell you what sources it’s using for any given output. Worse, it has a tendency to make up sources that don’t actually exist when you ask.
In addition, ChatGPT is not designed as a citation generator and cannot add correctly formatted citations to your work. Instead, try a tool designed for this purpose, like the Scribbr Citation Generator.
Fake “facts”
ChatGPT is not always trustworthy when it comes to giving you factually correct information. While it doesn’t deliberately lie, it also doesn’t have “knowledge” in a traditional sense, and it lacks the ability to verify its claims.
相反，它的反应是基于识别和复制它在其他文本中看到的模式。这意味着如果它不“知道”某件事，它就倾向于猜测。它的猜测是完全可信的，就像既定的事实一样。
因此，仔细检查ChatGPT所做的任何事实声明与更可靠的来源是非常重要的，不要引用ChatGPT作为您研究的事实信息来源。
其他有趣的文章
如果你想要更多关于使用人工智能工具、理解抄袭和引用来源的提示，请务必查看我们的其他一些文章，包括解释、示例和格式。
