ChatGPT's Handling of L2 Learners’ Fossilized Errors: A Linguistic Evaluation
DOI:
https://doi.org/10.70152/duties.v1i2.219Keywords:
Academic Writing, ChatGPT, Error Correction, EFL Learners, FossilizationArticle Metrics
Abstract
This study investigates ChatGPT’s capacity to address fossilized grammatical errors in English as a Foreign Language (EFL) learners’ academic writing. Through a mixed-methods design, a controlled corpus of 500 hypothetical sentences containing persistent error types, such as verb tenses, articles, prepositions, and non-idiomatic expressions, was submitted to ChatGPT-4. Quantitative analysis evaluated correction accuracy using standard metrics (precision, recall, F-score), while qualitative content analysis assessed the pedagogical appropriateness and consistency of ChatGPT’s feedback. Results showed high accuracy in correcting rule-based structures (e.g., subject-verb agreement), but significantly lower performance for context-sensitive and fossilized errors. While ChatGPT often provided clear corrections, its feedback frequently lacked explanatory depth, contextual sensitivity, and scaffolding necessary for promoting learner noticing and long-term acquisition. These findings suggest that although ChatGPT can effectively support surface-level proofreading, it cannot fully substitute the role of human instructors in addressing deeply ingrained L2 errors. The study emphasizes the importance of explainable AI, AI literacy, and hybrid instructional models that combine technological efficiency with pedagogical intentionality. It offers implications for educators, curriculum developers, and AI tool designers seeking to integrate language models into second language acquisition contexts.
References
Albelihi, H. H. M., & Al-Ahdal, A. (2024). Overcoming error fossilization in academic writing: Strategies for Saudi EFL learners to move beyond the plateau. Asian-Pacific Journal of Second and Foreign Language Education, 9(1), 75. https://doi.org/10.1186/s40862-024-00303-y
Ali, S. (2024). A multidimensional analysis of academic writing: A comparative study of Saudi and British university students’ writing. World Journal of English Language, 14(2), 452. https://doi.org/10.5430/wjel.v14n2p452
Alsaweed, W., & Aljebreen, S. (2024). Investigating the accuracy of ChatGPT as a writing error correction tool. International Journal of Computer-Assisted Language Learning and Teaching, 14(1), 1–18. https://doi.org/10.4018/IJCALLT.364847
Amin, M. M., Mao, R., Cambria, E., & Schuller, B. W. (2024). A wide evaluation of ChatGPT on affective computing tasks. IEEE Transactions on Affective Computing, 15(4), 2204–2212. https://doi.org/10.1109/TAFFC.2024.3419593
Barrot, J. S. (2023). Using automated written corrective feedback in the writing classrooms: Effects on L2 writing accuracy. Computer Assisted Language Learning, 36(4), 584–607. https://doi.org/10.1080/09588221.2021.1936071
Bucol, J. L., & Sangkawong, N. (2025). Exploring ChatGPT as a writing assessment tool. Innovations in Education and Teaching International, 62(3), 867–882. https://doi.org/10.1080/14703297.2024.2363901
Canagarajah, S. (2024). Decolonizing academic writing pedagogies for multilingual students. TESOL Quarterly, 58(1), 280–306. https://doi.org/10.1002/tesq.3231
Creswell, J. W., & Creswell, J. D. (2023). Research Design: Qualitative, quantitative and mixed methods approaches. In SAGE Publications,Inc.: Vol. Sixth Edit (Issue 1). SAGE Publications. https://medium.com/@arifwicaksanaa/pengertian-use-case- a7e576e1b6bf
Dentella, V., Günther, F., Murphy, E., Marcus, G., & Leivada, E. (2024). Testing AI on language comprehension tasks reveals insensitivity to underlying meaning. Scientific Reports, 14(1), 28083. https://doi.org/10.1038/s41598-024-79531-8
Fan, N. (2023). Exploring the effects of automated written corrective feedback on EFL
students’ writing quality: A mixed-methods study. Sage Open, 13(2). https://doi.org/10.1177/21582440231181296
Fei, X., Tang, Y., Zhang, J., Zhou, Z., Yamamoto, I., & Zhang, Y. (2024). Evaluating cognitive performance: Traditional methods vs. ChatGPT. DIGITAL HEALTH, 10. https://doi.org/10.1177/20552076241264639
Foody, G. M. (2023). Challenges in the real world use of classification accuracy metrics: From recall and precision to the Matthews correlation coefficient. PLOS ONE, 18(10), e0291908. https://doi.org/10.1371/journal.pone.0291908
Javier, D. R. C., & Moorhouse, B. L. (2024). Developing secondary school English language learners’ productive and critical use of ChatGPT. TESOL Journal, 15(2). https://doi.org/10.1002/tesj.755
Joseph, G. V., P, A., Thomas M, A., Jose, D., V Roy, T., & Prasad, M. P. (2024). Impact of digital literacy, use of AI tools and peer collaboration on AI assisted learning- perceptions of the university students. Digital Education Review, 45, 43–49. https://doi.org/10.1344/der.2024.45.43-49
Khasawneh, M. A. S. (2024). Investigating the impact of automated instruments used for assessing the writing skill: Perspectives of language e-learners. Research Journal in Advanced Humanities, 5(2). https://doi.org/10.58256/4fd2qt78
Kormos, J. (2023). The role of cognitive factors in second language writing and writing to learn a second language. Studies in Second Language Acquisition, 45(3), 622– 646. https://doi.org/10.1017/S0272263122000481
Kos, Ž., & Mažgon, J. (2025). The challenges of using large language models: Balancing traditional learning methods with new technologies in the pedagogy of sociology. Education Sciences, 15(2), 191. https://doi.org/10.3390/educsci15020191
Leon, A. J., & Vidhani, D. (2023). ChatGPT needs a chemistry tutor too. Journal of Chemical Education, 100(10), 3859–3865. https://doi.org/10.1021/acs.jchemed.3c00288
Li, D., Noordin, N., Ismail, L., & Cao, D. (2025). A systematic review of corpus-based instruction in EFL classroom. Heliyon, 11(2), e42016. https://doi.org/10.1016/j.heliyon.2025.e42016
Lin, S. (2024). Evaluating LLMs’ grammatical error correction performance in learner Chinese. PLOS ONE, 19(10), e0312881. https://doi.org/10.1371/journal.pone.0312881
Lipnevich, A. A., & Smith, J. K. (2022). Student – Feedback interaction model: Revised.
Studies in Educational Evaluation, 75, 101208. https://doi.org/10.1016/j.stueduc.2022.101208
Long, M. (2015). Second language acquisition and task-based language teaching (Vol.
, Issue 1). Wiley Blackwell.
Mahmoud, Z., Li, C., Zappatore, M., Solyman, A., Alfatemi, A., Ibrahim, A. O., & Abdelmaboud, A. (2023). Semi-supervised learning and bidirectional decoding for effective grammar correction in low-resource scenarios. PeerJ Computer Science, 9, e1639. https://doi.org/10.7717/peerj-cs.1639
Mannekote, A., Davies, A., Pinto, J. D., Zhang, S., Olds, D., Schroeder, N. L., Lehman, B., Zapata-Rivera, D., & Zhai, C. (2024). Large language models for whole-learner support: opportunities and challenges. Frontiers in Artificial Intelligence, 7. https://doi.org/10.3389/frai.2024.1460364
Mayer, R. E. (2024). The past, present, and future of the cognitive theory of multimedia learning. Educational Psychology Review, 36(1), 8. https://doi.org/10.1007/s10648- 023-09842-1
McDowell, L. (2023). Japanese scientists’ English for research publication purposes. Journal of English for Research Publication Purposes, 4(2), 109–139. https://doi.org/10.1075/jerpp.22007.mcd
Ouyang, F., Guo, M., Zhang, N., Bai, X., & Jiao, P. (2024). Comparing the effects of instructor manual feedback and ChatGPT intelligent feedback on collaborative programming in China’s higher education. IEEE Transactions on Learning Technologies, 17, 2173–2185. https://doi.org/10.1109/TLT.2024.3486749
Park, J.-H., & Ahn, S. (2022). L2 learners’ cognitive and behavioral engagement with written corrective feedback. English Teaching, 77(3), 133–152. https://doi.org/10.15858/engtea.77.3.202209.133
Qin, Y., Luo, Y., & Zhai, Y. (2023). French error type annotation for dictation: A platform with automatic error type annotation for French dictation exercises. Frontiers in Psychology, 13. https://doi.org/10.3389/fpsyg.2022.1075932
Siow Chin, C., Pillai, S., & Zainuddin, S. Z. (2021). Recasts, prompts and noticing: A comparative study. Studies in English Language and Education, 8(2), 416–441. https://doi.org/10.24815/siele.v8i2.18546
Suryanto, S., Habiburrahim, H., Akmal, S., Zainuddin, Z., Safrul, M. S., & Hanani, F. (2024). Scrutinizing the impacts of Grammarly application on students’ writing performance and perception. Jurnal Ilmiah Peuradeun, 12(2), 465. https://doi.org/10.26811/peuradeun.v12i2.1235
Szcześniak, K. (2023). There is more to learning words than meets the conscious eye. Roczniki Humanistyczne, 71(10sp), 139–154. https://doi.org/10.18290/rh237110sp- 7
Szcześniak, K. (2024). The noticing hypothesis and formulaic language. Learnability of non-salient language forms. Acta Psychologica, 248, 104372. https://doi.org/10.1016/j.actpsy.2024.104372
Wei, P., Wang, X., & Dong, H. (2023). The impact of automated writing evaluation on second language writing skills of Chinese EFL learners: a randomized controlled trial. Frontiers in Psychology, 14. https://doi.org/10.3389/fpsyg.2023.1249991
Widyasari, R., Zhang, T., Bouraffa, A., Maalej, W., & Lo, D. (2024). Explaining explanations: An empirical study of explanations in code reviews. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3708518
Williyan, A., Fitriati, S. W., Pratama, H., & Sakhiyya, Z. (2024). AI as co-creator: Exploring Indonesian EFL teachers’ collaboration with AI in content development. Teaching English With Technology, 24(2), 5–21. https://doi.org/10.56297/vaca6841/LRDX3699/RZOH5366
Xiao, Y., & Zhi, Y. (2023). An exploratory study of EFL learners’ use of ChatGPT for language learning tasks: Experience and perceptions. Languages, 8(3), 212. https://doi.org/10.3390/languages8030212
Yildiz, H., & Kuru Gonen, S. I. (2024). Automated writing evaluation system for feedback in the digital world: An online learning opportunity for English as a foreign language students. Turkish Online Journal of Distance Education, 25(3), 183–206. https://doi.org/10.17718/tojde.1169727
Zhang, X., & Zhang, R. (2023). Feedback, response, and learner development: A sociocultural approach to corrective feedback in second language writing. Sage Open, 13(1). https://doi.org/10.1177/21582440231157680
Ziqi, C., Xinhua, Z., Qi, L., & Wei, W. (2024). L2 students’ barriers in engaging with form and content-focused AI-generated feedback in revising their compositions. Computer Assisted Language Learning, 1–21. https://doi.org/10.1080/09588221.2024.2422478
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Zahratun Nufus, Saleman Mashood Warrah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright for this article is held by the authors under the Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0). The article may be used, shared, and adapted for any purpose with proper attribution and distribution under the same license. Full license details: https://creativecommons.org/licenses/by-sa/4.0/
