Human–AI Collaboration in Academic Writing Instruction: Calibrated Feedback Model for EAP
DOI :
https://doi.org/10.18192/olbij.v15i1.7773Mots-clés :
intelligence artificielle générative, écriture académique, rétroaction, ChatGPT, écriture en langue seconde, EAP, IA en éducationRésumé
Cette étude adopte un devis méthodologique mixte afin de comparer la rétroaction produite par un enseignant humain et par ChatGPT-3.5 sur des productions écrites d’étudiants. Elle examine la cohérence des notes attribuées, les perceptions des étudiants quant à l’utilité de la rétroaction, ainsi que le degré d’alignement de chaque forme de rétroaction avec les objectifs pédagogiques. Le corpus se compose de 30 étudiants de première année inscrits à un cours d’anglais académique (English for Academic Purposes, EAP) dans une université canadienne. Chaque étudiant a soumis deux dissertations argumentatives, évaluées indépendamment par l’enseignant et par ChatGPT-3.5 à travers trois phases de calibration. Les résultats indiquent que, bien que ChatGPT-3.5 identifie de manière constante les problèmes de surface et présente une forte convergence avec l’évaluation humaine, il se révèle moins efficace pour traiter la structure rhétorique et les nuances contextuelles. Les réponses des étudiants font ressortir une préférence marquée pour un modèle hybride de rétroaction, combinant l’immédiateté des commentaires générés par l’IA et la profondeur ainsi que la valeur pédagogique de la rétroaction enseignante. Grâce à des invites calibrées et à un (re)cadrage pédagogique, l’IA générative peut compléter efficacement la rétroaction humaine sans toutefois s’y substituer. Cette étude propose un modèle hybride de rétroaction dans lequel les enseignants de langues peuvent mobiliser l’IA générative pour soutenir l’évaluation formative tout en conservant une supervision pédagogique. Les résultats offrent des pistes pour intégrer l’IA générative à l’enseignement de l’écriture académique d’une manière qui préserve la qualité de l’enseignement et l’autonomie des apprenants.
Références
Barkaoui, K. (2010). Variability in ESL essay rating processes: The role of the rating scale and rater experience. Language Assessment Quarterly, 7(1), 54–74. https://doi.org/10.1080/15434300903464418
Bender, E. M., & Koller, A. (2020). Climbing towards NLU: On meaning, form, and understanding in the age of data. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 5185–5198. https://doi.org/10.18653/v1/2020.acl-main.463
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. https://doi.org/10.1191/1478088706qp063oa
Cotos, E. (2011). Potential of automated writing evaluation feedback. CALICO Journal, 28(2), 420–459. https://doi.org/10.11139/cj.28.2.420-459 Creswell, J. W., & Plano Clark, V. L. (2017). Designing and conducting mixed methods research (3rd ed.). SAGE.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv: 1810.04805. arXiv. https://arxiv.org/abs/1810.04805
Dikli, S. (2006). Automated essay scoring. Turkish Online Journal of Distance Education, 7(1), 49–62. https://dergipark.org.tr/en/pub/tojde/article/176620
Escalante, J., Pack, A., & Barrett, A. (2023). AI-generated feedback on writing: Insights into effcacy and ENL student preference. International Journal of Educational Technology in Higher Education, 20, Article 57. https://doi.org/10.1186/s41239-023-00425-2
Evmenova, A. S., Regan, K., Mergen, R., & Hrisseh, R. (2024). Improving writing feedback for struggling writers: Generative AI to the rescue? TechTrends, 68(4), 790–802. https://doi.org/10.1007/s11528-024-00965-y
Fan, Y., Tan, S., & Lim, G. Y. W. (2024). EAP teacher feedback in the age of AI: Supporting first-year students in EFL disciplinary writing. Australian Journal of Applied Linguistics, 7(3), 250–267. https://doi.org/10.29140/ajal.v7n3.1943
Farzi, R. (2024). Calibrating generative AI for second language writing assessment: Combining statistical validation with prompt design. Assessment and Practice in Educational Sciences, 2(4), 1–12. https://journalapes.com/index.php/apes/article/view/91
Ferris, D. R. (2014). Responding to student writing: Teachers’ philosophies and practices. Assessing Writing, 19, 6–23. https://doi.org/10.1016/j.asw.2013.09.004
Fleckenstein, J., Liebenow, L. W., & Meyer, J. (2023). Automated feedback and writing: A multi-level meta-analysis of effects on students’ performance. Frontiers in Artificial Intelligence, 6, Article 1162454. https://doi.org/10.3389/frai.2023.1162454
García-López, I. M., & Trujillo-Liñán, L. (2025). Ethical and regulatory challenges of generative AI in education: A systematic review. Frontiers in Education, 10, Article 1565938. https://doi.org/10.3389/feduc.2025.1565938
Gayed, J. M., Carlon, M. K. J., Oriola, A. M., & Cross, J. S. (2022). Exploring an AI-based writing assistant’s impact on english language learners. Computers and Education: Artificial Intelligence, 3, Article 100055. https://doi.org/10.1016/j.caeai.2022.100055
Harunasari, S. Y. (2023). Examining the effectiveness of AI-integrated approach in EFL writing: A case of ChatGPT. International Journal of Progressive Sciences and Technologies, 39(2), 357–368. https://doi.org/10.52155/ijpsat.v39.2.5516
Hyland, K. (2016). Teaching and researching writing (3rd ed.). Routledge.
Hyland, K., & Hyland, F. (Eds.). (2019). Feedback in second language writing: Contexts and issues (2nd ed.). Cambridge University Press. https://doi.org/10.1017/9781108635547
Kaliisa, R., Misiejuk, K., López-Pernas, S., & Saqr, M. (2026). How does artificial intelligence compare to human feedback? a meta-analysis of performance, feedback perception, and learning dispositions. Educational Psychology, 46(1), 80–111. https://doi.org/10.1080/01443410.2025.2553639
Karagoz, I. (2025). AI-generated feedback in english writing instruction for language learners: A systematic review. The Reading Matrix: An International Online Journal, 25(1), 51–67. https://www.readingmatrix.com/files/34-9gp90gjo.pdf
Landauer, T. K. (2003). Automatic essay assessment. Assessment in Education: Principles, Policy & Practice, 10(3), 295–308.
https://doi.org/10.1080/0969594032000148154
Lee, S. S., & Moore, R. L. (2024). Harnessing generative AI (GenAI) for automated feedback in higher education: A systematic review. Online Learning, 28(3), 82–104. https://doi.org/10.24059/olj.v28i3.4593
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2021). Retrieval-augmented generation for knowledge-intensive NLP tasks. arXiv. https://doi.org/10.48550/arXiv.2005.11401
Li, S. (2025). Generative AI and second language writing. Digital Studies in Language and Literature, 2(1), 122–152. https://doi.org/10.1515/dsll-2025-0007
Liang, W., Zhang, Y., Codreanu, M., Wang, J., Cao, H., & Zou, J. (2025). The widespread adoption of large language model-assisted writing across society. arXiv: 2502.09747. arXiv. https://arxiv.org/abs/2502.09747
Lund, B. D., Lee, T. H., Mannuru, N. R., & Arutla, N. (2025). AI and academic integrity: Exploring student perceptions and implications for higher education. Journal of Academic Ethics, 23(3), 1545–1565. https://doi.org/10.1007/s10805-025-09613-3
Luo, M., Hu, X., & Zhong, C. (2025). The collaboration of AI and teacher in feedback provision and its impact on EFL learners’ argumentative writing. Education and Information Technologies, 30, 17695–17715. https://doi.org/10.1007/s10639-025-13488-7
McNamara, T. (2000). Language testing. Oxford University Press.
Nelson, A. S., Santamaría, P. V., Javens, J. S., & Ricaurte, M. (2025). Students’ perceptions of generative artificial intelligence (GenAI) use in academic writing in english as a foreign language. Education Sciences, 15(5), Article 611. https://doi.org/10.3390/educsci15050611
Nguyen, A., Hong, Y., Dang, B., & Huang, X. (2024). Human-AI collaboration patterns in AI-assisted academic writing. Studies in Higher Education, 49(5), 847–864. https://doi.org/10.1080/03075079.2024.2323593
Nguyen, K. V. (2025). The use of generative AI tools in higher education: Ethical and pedagogical principles. Journal of Academic Ethics, 23, 1435–1455. https://doi.org/10.1007/s10805-025-09607-1
OECD. (2026). OECD digital education outlook 2026: Exploring effective uses of generative AI in education. https://doi.org/10.1787/062a7394-en
Ogunleye, B., Zakariyyah, K. I., Ajao, O., Olayinka, O., & Sharma, H. (2024). A systematic review of generative AI for teaching and learning practice. Education Sciences, 14(6), Article 636. https://doi.org/10.3390/educsci14060636
OpenAI. (2023). ChatGPT (GPT-3.5). https://chatgpt.com/
OpenAI. (2025). ChatGPT (GPT-5). https://chatgpt.com/
Page, E. B. (2003). Project essay grade: PEG. In M. D. Shermis & J. Burstein (Eds.), Automated essay scoring: A cross-disciplinary perspective (pp. 43–54). Lawrence Erlbaum Associates.
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI.
https://cdn.openai.com/better-languagemodels/language_models_are_unsupervised_multitask_learners.pdf
Rana, A., Vaidya, P., & Hu, Y. C. (2026). Transformative role of large language models in education and comparative analysis with traditional technologies. Education and Information Technologies, 31(4), 1137–1162. https://doi.org/10.1007/s10639-025-13854-5
Samala, A. D., Rawas, S., Wang, T., Reed, J. M., Kim, J., Howard, N.-J., & Ertz, M. (2024). Unveiling the landscape of generative artificial intelligence in education: A comprehensive taxonomy of applications, challenges, and future prospects. Education and Information Technologies, 30, 3239–3278. https://doi.org/10.1007/s10639-024-12936-0
Shi, H., & Aryadoust, V. (2024). A systematic review of AI-based automated written feedback research. ReCALL, 36(2), 187–209.
https://doi.org/10.1017/S0958344023000265
Steiss, J., Tate, T., Graham, S., Cruz, J., Hebert, M., Wang, J., & Olson, C. B. (2024). Comparing the quality of human and ChatGPT feedback on students’ writing. Learning and Instruction, 91, Article 101894. https://doi.org/10.1016/j.learninstruc.2024.101894
Uludag, P., & McDonough, K. (2022). Validating a rubric for assessing integrated writing in an EAP context. Assessing Writing, 52, Article 100609. https://doi.org/10.1016/j.asw.2022.100609
van Niekerk, J., Delport, P. M., & Sutherland, I. (2025). Addressing the use of generative AI in academic writing. Computers and Education: Artificial Intelligence, 8, Article 100342. https://doi.org/10.1016/j.caeai.2024.100342
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008. https://proceedings.neurips.cc/paper/7181-attention-is-all-you-need
Wang, D. (2024). Teacher- versus AI-generated (Poe application) corrective feedback and language learners’ writing anxiety, complexity, fluency, and accuracy. The International Review of Research in Open and Distributed Learning, 25(3), 37–56. https://doi.org/10.19173/irrodl.v25i3.7646
Zhai, C., Wibowo, S., & Li, L. D. (2024). The effects of over-reliance on AI dialogue systems on students’ cognitive abilities: A systematic review. Smart Learning Environments, 11(1), Article 28. https://doi.org/10.1186/s40561-024-00316-7
Zhang, Z., Aubrey, S., Huang, X., & Chiu, T. K. F. (2025). The role of generative AI and hybrid feedback in improving L2 writing skills: A comparative study. Innovation in Language Learning and Teaching. Advance online publication. https://doi.org/10.1080/17501229.2025.2503890
Téléchargements
Publié-e
Numéro
Rubrique
Licence
© Reza Farzi 2026
Cette œuvre est sous licence Creative Commons Attribution 4.0 International.
Les auteurs qui publient avec Les Cahiers de l'ILOB acceptent les termes suivants:
- Les auteurs conservent le droit d'auteur et accordent à la revue le droit de première publication, l'ouvrage étant alors disponible simultanément, sous la licence Licence d’attribution Creative Commons permettant à d'autres de partager l'ouvrage tout en en reconnaissant la paternité et la publication initiale dans cette revue.
- Les auteurs peuvent conclure des ententes contractuelles additionnelles et séparées pour la diffusion non exclusive de la version imprimée de l'ouvrage par la revue (par ex., le dépôt institutionnel ou la publication dans un livre), accompagné d'une mention reconnaissant sa publication initiale dans cette revue.
- Les auteurs ne soumettront pas simultanément le même travail pour publication à plus d’une revue spécialisée à la fois.
