FEEDBACK QUALITY OF CHATGPT IN REVISING FRENCH TEXTS
DOI:
https://doi.org/10.18173/2354-1075.2025-0034Keywords:
ChatGPT, text revising, feedback quality, overcorrectionAbstract
This study investigates the effectiveness of ChatGPT's feedback in revising French texts written by A2+ level learners. ChatGPT's feedback was divided into three categories: error detection, error analysis, and correction suggestion. A mixed-methods analysis of 20 learner texts showed that the AI's rate of inaccurate error detection was 13%, bad error analysis was 18%, and bad correction suggestion was 16%. Over half of the incorrect feedback was overcorrection, while 29% of the flawed error analysis was due to ChatGPT's lack of meta-linguistic knowledge to correctly explain the nature of the error. While most studies on the application of ChatGPT in foreign language teaching use questionnaires as the corpus, this research uses authentic texts, providing a more nuanced insight into the limitations of this tool. The study recommends that teachers, when applying ChatGPT in writing instruction, create prompts that clearly specify the language level of the text and the target audience. In cases of ineffective feedback, students should provide additional instructions to ChatGPT by clarifying their intended meaning or specifying the desired language norm.
Downloads
References
[1] 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.
[2] Baskara R, (2023). Exploring the implications of ChatGPT for language learning in higher education. Indonesian Journal of English Language Teaching and Applied Linguistics, 7(2), 343-358.
[3] Diallo M F, (2023). Ce que ChatGPT fait à l’enseignement, à la recherche et aux organisations (What ChatGPT does for education, research and organizations). Revue française de gestion, 312(5), 9-14. (in French)
[4] Dimeli M & Kostas A, (2025). The Role of ChatGPT in Education: Applications, Challenges: Insights From a Systematic Review. Journal of Information Technology Education. Research, 24, 2.
[5] Fokides E & Peristeraki E, (2024). Comparing ChatGPT's correction and feedback comments with that of educators in the context of primary students' short essays written in English and Greek. Education and Information Technologies, 1-45.
[6] Genre S & Similowski K, (2024). Enseigner et apprendre avec ChatGPT en milieu universitaire français (Teaching and learning with ChatGPT in a French university environment). 91e congrès de l’ACGAS, Colloque 524, Enseigner, former, apprendre avec l’IA et le numérique: quelles valeurs ? (in French)
[7] H Huu & L T Dieu, (2024). Designing real-world statistics problems on central tendency of ungrouped data using ChatGPT 3.5. Journal of Science Educational Science, 69(5B), 83-98. https://doi.org/10.18173/2354-1075.2024-0137
[8] 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
[9] Woodworth J & Barkaoui K, (2020). Perspectives on using automated writing evaluation systems to provide written corrective feedback in the ESL classroom. TESL Canada Journal, 37(2), 234-247.
[10] Oriol-Boyer C, (2000). Contribution de Claudette Oriol-Boyer (Contribution by Claudette Oriol-Boyer). Pratiques, 105(1), 218-221. (in French)
[11] Do T B T, (2023). Effects of Scaffolded Peer Review Training on Revision Quantity and Quality in Foreign Language Writing. Iranian Journal of Language Teaching Research, 11(2), 55-73.
[12] Fang T, Yang S, Lan K, Wong D F, Hu J, Chao L S & Zhang Y, (2023). Is ChatGPT a highly fluent grammatical error correction system? A comprehensive evaluation. arXiv. Prépublication. https://doi.org/10.48550/arXiv.2304.01746
[13] Wu H, Wang W, Wan Y, Jiao W & Lyu M, (2023). ChatGPT or Grammarly? Evaluating ChatGPT on grammatical error correction benchmark. arXiv preprint arXiv:2303.13648.
[14] Bok E & Cho Y, (2023). Examining Korean EFL college students’ experiences and perceptions of using ChatGPT as a writing revision tool. Journal of English Teaching through Movies and Media, 24(4), 15-27. https://doi.org/10.16875/stem.2023.24.4.15
[15] Su Y, Lin Y & Lai C, (2023). Collaborating with ChatGPT in argumentative writing classrooms. Assessing Writing, 57, article 100752. https://doi.org/10.1016/j.asw.2023.100752
[16] Kurt G & Kurt Y, (2024). Enhancing L2 writing skills: ChatGPT as an automated feedback tool. Journal of Information Technology Education: Research, 23, 024.
[17] Yoon S Y, Miszoglad E & Pierce L R, (2023). Evaluation of ChatGPT feedback on ELL writers’ coherence and cohesion. arXiv preprint arXiv:2310.06505. https://doi.org/10.48550/arXiv.2310.06505
[18] Holmes T, (2024). L’utilisation de ChatGPT 3.5 pour la rétroaction corrective écrite interactive en enseignement-apprentissage du français langue seconde: une étude exploratoire (The use of ChatGPT 3.5 for interactive written corrective feedback in teaching and learning French as a second language: an exploratory study). Actes des Journées de linguistique, 1, 17-30. (in French)
[19] El Karfa I, (2024). ChatGPT: un outil pour améliorer les compétences rédactionnelles et argumentatives des élèves (ChatGPT: a tool to improve students’ writing and argumentative skills). Le français aujourd’hui, 226(3), 51-68. (in French)
[20] Burston J, (2008). Review of BonPatron: An online spelling, grammar, and expression checker. Calico Journal, 25(2), 337-347.
[21] Lavolette E, Polio C & Kahng J, (2015). The accuracy of computer-assisted feedback and students’ responses to it. Language, Learning & Technology, 19(2).
[22] Butterfield E, Hacker D & Albertson L, (1996). Environmental, cognitive and metacognitive influences on text revision: Assessing the evidence. Educational Psychology Review, 8(3), 239-260.
[23] ĐTB Thủy, (2024). Độ chuẩn xác của công cụ sửa lỗi MerciApp trong dạy viết tiếng Pháp. Tạp chí Khoa học Giáo dục Việt Nam, 20(6), 22-27. DOI: 10.15625/2615-8957/12410604.
[24] Hoang GTL, (2022). Feedback Precision and Learners' Responses: A Study into ETS” Criterion” Automated Corrective Feedback in EFL Writing Classrooms. JALT CALL Journal, 18(3), 444-467.
