Reflexivity in human-written and ChatGPT-generated English research article abstracts: A comparison of metadiscourse
The DOI matches its Crossref record; 72 of the 72 references it cites were found in a registry or an index.
Abstract
This study compares metadiscourse in human-written and ChatGPT-generated research article abstracts and finds metadiscourse markers more prevalent in ChatGPT-generated abstracts.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In contrast, Zhang and Zhang (2025) found that ChatGPT-generated research abstracts contained more metadiscourse markers overall than human abstracts, with human writers favoring self-oriented (writer-introducing) markers and ChatGPT favoring text-oriented introductions.”
From Metadiscourse Patterns in Human-Written vs. Generative AI-Authored Research Abstracts: A Comparative Corpus-Based Analysis (2026) · cites this paper as Zhang and Zhang (2025)
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Cohen, J. (1992) · Psychological Bulletin · doi:10.1037//0033-2909.112.1.155 · Cited by 8,771
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
New Effect Size Rules of Thumb
Sawilowsky, S. S. (2009) · Journal of Modern Applied Statistical Methods · doi:10.22237/jmasm/1257035100 · Cited by 3,254
Chatting and cheating: Ensuring academic integrity in the era of ChatGPT
Cotton, D. R. E., Cotton, P. A., & Shipway, J. R. (2024) · Innovations in Education and Teaching International · doi:10.1080/14703297.2023.2190148 · Cited by 3,087
Chatting and Cheating. Ensuring academic integrity in the era of ChatGPT
Cotton, D., Cotton, P., & Shipway, J. R. (2023) · doi:10.35542/osf.io/mrz8h · Cited by 3,079
Ray, P. P. (2023) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.04.003 · Cited by 2,463
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Self-citationA Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.18223 · Cited by 2,090
Self-citationDisciplinary Discourses: Social Interactions in Academic Writing
Sun, J., & Hyland, K. (2001) · TESOL Quarterly · doi:10.2307/3587657 · Cited by 1,970
Academic tribes and territories
Becher, T., & Trowler, P. (1989) · Cited by 1,932
The characteristics of subject matter in different academic areas.
Biglan, A. (1973) · Journal of Applied Psychology · doi:10.1037/h0034701 · Cited by 1,766
Analysing genre: Language use in professional settings
Drury, H. (1995) · English for Specific Purposes · doi:10.1016/0889-4906(95)90021-7 · Cited by 1,528
Shifters, linguistic categories, and cultural description
Silverstein, M. C. (1976) · Medical Entomology and Zoology · Cited by 1,444
Metadiscourse: Exploring Interaction in Writing
Paltridge, B. (2007) · Journal of Pragmatics · doi:10.1016/j.pragma.2006.07.003 · Cited by 1,226
Gao, 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
ChatGPT and other large language models are double-edged swords
Shen, Y., Heacock, L., Elias, J., Hentel, K. D., Reig, B., Shih, G., & Moy, L. (2023) · Radiology · doi:10.1148/radiol.230163 · Cited by 1,008
Using ChatGPT for second language writing: pitfalls and potentials
Barrot, J. S. (2023) · Assessing Writing · doi:10.1016/j.asw.2023.100745 · Cited by 770
CRISMORE, A., MARKKANEN, R., & STEFFENSEN, M. S. (1993) · Written Communication · doi:10.1177/0741088393010001002 · Cited by 743
Metadiscourse in L1 and L2 English
Ädel, A. (2006) · Studies in Corpus Linguistics · doi:10.1075/scl.24 · Cited by 662
ChatGPT for (Finance) research: The Bananarama Conjecture
Dowling, M., & Lucey, B. (2023) · Finance Research Letters · doi:10.1016/j.frl.2023.103662 · Cited by 591
Lenhard, W., & Lenhard, A. (2017) · doi:10.13140/rg.2.2.17823.92329 · Cited by 526
Genre Knowledge in Disciplinary Communication
Berkenkotter, C., & Huckin, T. N. (2016) · Routledge eBooks · doi:10.4324/9781315538747 · Cited by 481
Lyons, J. (1977) · Cambridge University Press eBooks · doi:10.1017/cbo9781139165693 · Cited by 448
The Use of Personal Pronouns: Role Relationships in Scientific Journal Articles
Kuo, C.-H. (1999) · English for Specific Purposes · doi:10.1016/s0889-4906(97)00058-6 · Cited by 427
Persuasion and context: The pragmatics of academic metadiscourse
Hyland, K. (1998) · Journal of Pragmatics · doi:10.1016/s0378-2166(98)00009-5 · Cited by 422
Hu, G., & Cao, F. (2011) · Journal of Pragmatics · doi:10.1016/j.pragma.2011.04.007 · Cited by 408
How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection
Guo, B., Zhang, X., Wang, Z., Jiang, M., Nie, J., Ding, Y., Yue, J., & Wu, Y. (2023) · arXiv · doi:10.48550/arxiv.2301.07597 · Cited by 318
Academic Voices: Across languages and disciplines
Fløttum, K., Dahl, T., & Kinn, T. (2006) · Pragmatics & Beyond New Series · doi:10.1075/pbns.148 · Cited by 311
Interactional metadiscourse in research article abstracts
Gillaerts, P., & Van de Velde, F. (2010) · Journal of English for Academic Purposes · doi:10.1016/j.jeap.2010.02.004 · Cited by 304
‘Nowhere has anyone attempted … In this article I aim to do just that’
Harwood, N. (2005) · Journal of Pragmatics · doi:10.1016/j.pragma.2005.01.012 · Cited by 272
Cultural Differences in Academic Rhetoric.: A Textlinguistic Study.
Mauranen, A. (1993) · Peter Lang eBooks · Cited by 269
Change of Attitude? A Diachronic Study of Stance
Hyland, K., & Jiang, F. (. (2016) · Written Communication · doi:10.1177/0741088316650399 · Cited by 268
Is academic writing becoming more informal?
Hyland, K., & Jiang, F. (. (2017) · English for Specific Purposes · doi:10.1016/j.esp.2016.09.001 · Cited by 267
“In this paper we suggest”: Changing patterns of disciplinary metadiscourse
Hyland, K., & Jiang, F. (. (2018) · English for Specific Purposes · doi:10.1016/j.esp.2018.02.001 · Cited by 261
Disciplinary Identities: Individuality and Community in Academic Discourse
Hyland, K. (2012) · doi:10.1017/9781009406512 · Cited by 248
Some Exploratory Discourse on Metadiscourse
Kopple, W. V. (1985) · College Composition & Communication · doi:10.58680/ccc198511781 · Cited by 225
Ädel, A. (2010) · Nordic Journal of English Studies · doi:10.35360/njes.218 · Cited by 221
Lexical Bundles and Disciplinary Variation in University Students’ Writing: Mapping the Territories
Durrant, P. (2017) · Applied Linguistics · doi:10.1093/applin/amv011 · Cited by 216
Discourse Reflexivity - A Discourse Universal? The Case of ELF
Mauranen, A. (2010) · Nordic Journal of English Studies · doi:10.35360/njes.216 · Cited by 207
Disciplinary and paradigmatic influences on interactional metadiscourse in research articles
Hu, G., & Cao, F. (2015) · English for Specific Purposes · doi:10.1016/j.esp.2015.03.002 · Cited by 201
The Subjective View: Secondary Qualities and Indexical Thoughts.
Averill, E. W., & McGinn, C. (1985) · The Philosophical Review · doi:10.2307/2185441 · Cited by 190
Writing with attitude: Stance expression in learner and professional dentistry research reports
Crosthwaite, P. R., Cheung, L., & Jiang, F. K. (2017) · English for Specific Purposes · doi:10.1016/j.esp.2017.02.001 · Cited by 157
Khedri, M., Heng, C. S., & Ebrahimi, S. F. (2013) · Discourse Studies · doi:10.1177/1461445613480588 · Cited by 141
Corpus Linguistics and Statistics with R
Desagulier, G. (2017) · Quantitative methods in the humanities and social sciences · doi:10.1007/978-3-319-64572-8 · Cited by 122
Designing and Evaluating Language Corpora
Egbert, J., Biber, D., & Gray, B. (2022) · Cambridge University Press eBooks · doi:10.1017/9781316584880 · Cited by 121
Zhou, T., Cao, S., Zhou, S., Zhang, Y., & He, A. (2023) · System · doi:10.1016/j.system.2023.103141 · Cited by 103
Diversity and Standards in Writing for Publication in the Age of AI—Between a Rock and a Hard Place
Kuteeva, M., & Andersson, M. (2024) · Applied Linguistics · doi:10.1093/applin/amae025 · Cited by 91
Promotion and Politeness: Conflicting Scholarly Rhetoric in Three Disciplines
Lindeberg, A.-C. (2004) · Doria (University of Helsinki) · Cited by 85
Cluster Analysis for Corpus Linguistics
Moisl, H. L. (2015) · De Gruyter eBooks · doi:10.1515/9783110363814 · Cited by 84
A multidimensional analysis of metadiscourse markers across written registers
Zhang, M. (2016) · Discourse Studies · doi:10.1177/1461445615623907 · Cited by 82
Self-citationLi, Z. (2021) · Journal of English for Academic Purposes · doi:10.1016/j.jeap.2021.100977 · Cited by 63
Hwang, T., Aggarwal, N., Khan, P. Z., Roberts, T., Mahmood, A., Griffiths, M. M., Parsons, N., & Khan, S. (2024) · PLOS ONE · doi:10.1371/journal.pone.0297701 · Cited by 59
Kong, X., & Liu, C. (2024) · Journal of English for Academic Purposes · doi:10.1016/j.jeap.2024.101432 · Cited by 57
El‐Dakhs, D. A. S. (2018) · Research in Language · doi:10.2478/rela-2018-0002 · Cited by 50
Dynel, M. (2023) · Language & Communication · doi:10.1016/j.langcom.2023.09.002 · Cited by 46
Reflexively Speaking: Metadiscourse in English as a Lingua Franca
Mauranen, A. (2023) · De Gruyter eBooks · doi:10.1515/9783110295498 · Cited by 45
Beyond the Front Yard: The Dehumanizing Message of Accent-Altering Technology
Payne, A. L., Austin, T., & Clemons, A. M. (2024) · Applied Linguistics · doi:10.1093/applin/amae002 · Cited by 41
Ädel, A. (2021) · English for Specific Purposes · doi:10.1016/j.esp.2021.09.001 · Cited by 38
Arabic and English abstracts in bilingual language science journals: Same or different?
Alharbi, L. M., & Swales, J. M. (2011) · Languages in Contrast · doi:10.1075/lic.11.1.06alh · Cited by 28
American National standard for writing abstracts
(1977) · IEEE Transactions on Professional Communication · doi:10.1109/tpc.1977.6591959 · Cited by 20
Author self-reference: A cross-linguistic/cultural and cross-disciplinary analysis
Dong, J., Du, K., & Buckingham, L. (2024) · Journal of English for Academic Purposes · doi:10.1016/j.jeap.2024.101352 · Cited by 16
Exploring Personal Metadiscourse Markers across Speech and Writing Using Cluster Analysis
Zhang, M. (2018) · Journal of Quantitative Linguistics · doi:10.1080/09296174.2018.1480856 · Cited by 15
Self-citationVariation in Metadiscourse across Speech and Writing: A Multidimensional Study
Zhang, M. (2022) · Applied Linguistics · doi:10.1093/applin/amac012 · Cited by 14
Self-citationIt takes one to know one—Machine learning for identifying OBGYN abstracts written by ChatGPT
Levin, G., Meyer, R., Guigue, P., & Brezinov, Y. (2024) · International Journal of Gynecology & Obstetrics · doi:10.1002/ijgo.15365 · Cited by 12
Metadiscourse in Academic Speech
Aguilar, M. (2009) · Peter Lang CH eBooks · doi:10.3726/978-3-0351-0403-5 · Cited by 11
Will ChatGPT-4 improve the quality of medical abstracts?
Gravel, J., Dion, C., Kermani, M. F., Mousseau, S., & Osmanlliu, E. (2024) · Paediatrics & Child Health · doi:10.1093/pch/pxae062 · Cited by 10
(2021) · Applied Linguistics · doi:10.1093/applin/amab001 · Cited by 6
OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.08774
McGinn, C. (n.d.) · Routledge Encyclopedia of Philosophy · doi:10.4324/9780415249126-v032-1
Historical discourse analysis: Scientific language and changing thought-styles
Taavitsainen, I. (2002) · Current Issues in Linguistic Theory · doi:10.1075/cilt.224.14taa
Research works printed but not linked: 3
- Abu-Bader, 2021, Using
- Harris, 1959, ‘The Transformational Model of Language Structure’, Anthropological Linguistics, 1, 27
- Huckin, 2006, ‘Abstracting from Abstracts’,, 93
Cited by
Zhang, M., & Zhang, J. (2025) · Journal of English for Academic Purposes · doi:10.1016/j.jeap.2025.101540 · Cited by 17
Self-citationExemplification in ChatGPT and student argumentative writing: A local grammar analysis
Jiang, F. K., & Su, H. (2026) · Linguistics and Education · doi:10.1016/j.linged.2026.101533 · Cited by 4
Sadigzade, Z. (2026) · Acta Globalis Humanitatis et Linguarum · doi:10.69760/aghel.026001005 · Cited by 1
Metapragmatic acts performed by ChatGPT 4o and human authors in research article (RA) abstracts
Gao, Y., Chen, X., & Zhang, J. (2026) · English for Specific Purposes · doi:10.1016/j.esp.2026.05.007
Self-citation
Metadata
- Authors
- Zhang, M., & Zhang, J.
- Affiliations
- Guangdong University of Foreign Studies (CN)
- Central China Normal University (CN)
- Corresponding author
- Zhang, Man
- Venue
- Applied Linguistics
- Publisher
- Oxford University Press (OUP)
- Published
- 2025-06-04
- Volume
- 47
- Issue
- 3
- Pages
- 656-676
- ISSN
- 0142-6001 (ISSN-L)
- 1477-450X
- OpenAlex
- W4411074631
- Cited by
- 7
- References
- 66
- Citations by year
- 2026: 6 · 2025: 1
- FWCI
- 67.67
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Applied Linguistics (publishedVersion)
- Funders
- National Social Science Fund of China (22BYY012)
- Topics
- Social Sciences › Linguistics and Language › Discourse Analysis in Language Studies
- Social Sciences › Linguistics and Language › Linguistics and Discourse Analysis
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Keywords
- reflexivity, metadiscourse, ChatGPT, large language models, research article abstracts, metadiscourse markers, discourse functions, English academic writing
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
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.