Identifying ChatGPT-Generated Texts in EFL Students’ Writing: Through Comparative Analysis of Linguistic Fingerprints
Open accessAbstract
The emergence of generative AI (GenAI) poses new challenges for L2 writing teachers. This study investigates the distinguishability of essays written by Japanese EFL learners from those generated by ChatGPT. Partially replicating Herbold et al. (2023), 140 first-year university students wrote essays and completed a survey on ChatGPT use. Among them, 125 wrote independently, 13 used ChatGPT for proofreading, and two asked ChatGPT to write the entire essay. To create a comparative dataset, 123 additional essays were generated by ChatGPT, imitating the two texts. The resulting 263 essays were then analyzed using the natural language processing (NLP) technique, including automated linguistic analysis and machine learning classification using random forest. The results reveal significant differences between human-written and ChatGPT-generated essays across all linguistic features, with the latter being easily identifiable. This study emphasizes the need for clear guidelines on the ethical use of AI in L2 writing, highlighting the potential risk of inappropriate AI use and the importance of fostering a mutual understanding of AI use with learners regarding responsible AI integration in academic work.
Integrity signals
Registry
Cites
Statistics
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?
Linguistic fingerprinting can distinguish ChatGPT from EFL prose at fine-grained levels.
“Linguistic fingerprinting can distinguish ChatGPT from EFL prose at these fine-grained levels”
From ARE AI DETECTORS FAIR TO EFL LEARNERS? A LIBRARY RESEARCH ON DETECTION BIAS AND ACADEMIC INTEGRITY (2026) · cites this paper as Mizumoto et al., 2024
The citation lists haven’t been fetched yet
References 58 · Cited by 58
- Authors
- Mizumoto, A., Yasuda, S., & Tamura, Y.
- Affiliations
- Kansai University (JP)
- Kobe University (JP)
- Corresponding author
- Mizumoto, Atsushi
- Venue
- Applied Corpus Linguistics
- Publisher
- Elsevier BV
- Published
- 2024-12
- Volume
- 4
- Issue
- 3
- Pages
- 100106
- ISSN
- 2666-7991 (ISSN-L)
- OpenAlex
- W4402893311
- Cited by
- 58
- References
- 58
- Citations by year
- 2026: 30 · 2025: 27 · 2024: 1
- FWCI
- 8.59
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Applied Corpus Linguistics (publishedVersion, cc-by-nc)
- Funders
- Japan Society for the Promotion of Science (23H00072)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Keywords
- ChatGPT, generative AI detection, EFL writing, second language writing, essay writing, AI ethics in education, Japanese EFL learners, random forest classification
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
