The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Does ChatGPT Argue Like Students? Bundles in Argumentative Essays
Abstract
The advent of ChatGPT, a novel AI-powered language model able to create grammatically accurate and coherent texts, has generated considerable concern among educationalists anxious about its potential to enable cheating among students and to undermine the development of critical thinking, problem-solving, and literacy skills. The similarities and differences between ChatGPT texts and human writing, however, remain underexplored. This study aims to bridge this gap by comparing the use of 3-word bundles in A-level argumentative essays written by British students with those generated by ChatGPT. Our findings show that ChatGPT essays contain a lower frequency of bundles but these have a higher type/token ratio, suggesting that its bundles are more rigid and formulaic. We also found noun and preposition-based bundles are more prevalent in ChatGPT texts, employed for abstract descriptions and to provide transitional and structuring cues. Student essays are characterized by more epistemic stances and authorial presence, crucial in persuasive argumentation. We attribute these distinct patterns in ChatGPT’s output to its processing of vast training data and underlying statistical algorithms. The study points to pedagogical implications for incorporating ChatGPT in writing instruction.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Longman Grammar of Spoken and Written English
Broussard, K. M., Biber, D., Johansson, S., Leech, G., Conrad, S., & Finegan, E. (2000) · TESOL Quarterly · doi:10.2307/3587792 · Cited by 8,193
The Cambridge Grammar of the English Language
Huddleston, R., & Pullum, G. K. (2002) · Cambridge University Press eBooks · doi:10.1017/9781316423530 · Cited by 4,136
Stance and engagement: a model of interaction in academic discourse
Hyland, K. (2005) · Discourse Studies · doi:10.1177/1461445605050365 · Cited by 1,998
Self-citationChatGPT: five priorities for research
van Dis, E. A. M., Bollen, J., Zuidema, W., van Rooij, R., & Bockting, C. L. (2023) · Nature · doi:10.1038/d41586-023-00288-7 · Cited by 1,842
If you look at …: Lexical Bundles in University Teaching and Textbooks
Biber, D. (2004) · Applied Linguistics · doi:10.1093/applin/25.3.371 · Cited by 1,539
ChatGPT for Language Teaching and Learning
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023) · RELC Journal · doi:10.1177/00336882231162868 · Cited by 1,371
As can be seen: Lexical bundles and disciplinary variation
Hyland, K. (2008) · English for Specific Purposes · doi:10.1016/j.esp.2007.06.001 · Cited by 1,250
Self-citationGao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00819-6 · Cited by 1,099
An Academic Formulas List: New Methods in Phraseology Research
Simpson-Vlach, R., & Ellis, N. C. (2010) · Applied Linguistics · doi:10.1093/applin/amp058 · Cited by 863
Lexical bundles in published and student disciplinary writing: Examples from history and biology
Cortes, V. (2004) · English for Specific Purposes · doi:10.1016/j.esp.2003.12.001 · Cited by 839
Research works printed but not linked: 4
- Halliday, 1994, Functional grammar
- Hyland, 2005, Metadiscourse
- Murgia, 2023, ‘Generative AI exists because of the transformer,’, Financial Times
- Skrabut, 2023, 80 ways to use ChatGPT in the classroom: Using AI to enhance teaching and learning
Cited by
Li, B., Tan, Y. L., Wang, C., & Lowell, V. L. (2025) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2025.100445 · Cited by 285
Do LLMs write like humans? Variation in grammatical and rhetorical styles
Reinhart, A., Markey, B., Laudenbach, M., Pantusen, K., Yurko, R., Weinberg, G., & Brown, D. W. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2422455122 · Cited by 107
Mo, Z., & Crosthwaite, P. R. (2025) · Journal of English for Academic Purposes · doi:10.1016/j.jeap.2025.101499 · Cited by 87
Generative AI and Second Language Writing
Li, S. (2025) · Digital studies in language and literature · doi:10.1515/dsll-2025-0007 · Cited by 111
“In direct methods, human writers and GenAI are asked to write essays based on the same prompt, and a corpus analysis is conducted to identify the differences and commonalities between the two sets of essays (Jiang and Hyland 2024).”
InfluentialDoes ChatGPT Write Like a Student? Engagement Markers in Argumentative Essays
Jiang, F. (., & Hyland, K. (2025) · Written Communication · doi:10.1177/07410883251328311 · Cited by 52
“Interestingly, Jiang and Hyland (2024) similarly identified significantly fewer 3-word stance bundles (e.g., it is possible, this never is, in my opinion ) in the ChatGPT essays than used by human writers.”
Self-citation
Metadata
- Authors
- Jiang, F. (., & Hyland, K.
- Affiliations
- Jilin University (CN)
- University of East Anglia (GB)
- Corresponding author
- Jiang, Feng (Kevin)
- Venue
- Applied Linguistics
- Publisher
- Oxford University Press (OUP)
- Published
- 2024-08-20
- Volume
- 46
- Issue
- 3
- Pages
- 375-391
- ISSN
- 0142-6001 (ISSN-L)
- 1477-450X
- OpenAlex
- W4401976536
- Cited by
- 76
- References
- 37
- Citations by year
- 2026: 31 · 2025: 43 · 2024: 2
- FWCI
- 341.72
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Applied Linguistics (publishedVersion)
- UEA Digital Repository (University of East Anglia) (submittedVersion)
- Topics
- Social Sciences › Linguistics and Language › Discourse Analysis in Language Studies
- Social Sciences › Psychology › Developmental and Educational Psychology › Second Language Acquisition and Learning
- Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
- Keywords
- ChatGPT, argumentative essay, student writing, AI-generated text, type-token ratio, epistemic stance, authorial presence, persuasive argumentation, writing instruction, formulaic language
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Does ChatGPT Argue Like Students? Bundles in Argumentative Essays. https://app.cochat.ai/papers/10.1093/applin/amae052
- The paper
- Jiang, F. (., & Hyland, K. (2025). Does ChatGPT Argue Like Students? Bundles in Argumentative Essays. Applied Linguistics. https://doi.org/10.1093/applin/amae052
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.