10.57647/jals.2025.0502.08

The Effect of AI-assisted feedback vs Teacher corrective feedback on Iranian EFL Learners' Grammatical accuracy

PDF
  • Fatemeh Khodaie Alvar1,
  • Farnaz Sahebkheir*2,
  1. Department of English Language and Literature, Payame Noor University, Iran
  2. Department of English Language Teaching, Ta.C., Islamic Azad University, Tabriz, Iran

Received: 2025-06-22

Revised: 2025-12-22

Accepted: 2025-12-25

Published in Issue 2025-12-30

Copyright (c) 2025 Fatemeh Khodaie Alvar, Farnaz Sahebkheir (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Khodaie Alvar, F., & Sahebkheir, F. (2025). The Effect of AI-assisted feedback vs Teacher corrective feedback on Iranian EFL Learners’ Grammatical accuracy. Journal of Applied Linguistics Studies, 5(2). https://doi.org/10.57647/jals.2025.0502.08
Crossref
Scopus
Google Scholar
Europe PMC

PDF views: 0

Abstract

Accurate feedback is essential for developing grammatical accuracy in writing, yet large classes and limited teacher time often constrain feedback quality in Iranian institutes. Building on recent advances in large-language-model (LLM) technology, this study compared the efficacy of AI-assisted corrective feedback, delivered through ChatGPT-4, with traditional teacher-provided feedback. Forty pre-intermediate Iranian EFL learners (age = 18–25; 20 male, 20 female) from Daneshvarane Bartar English Institute in Tabriz, East Azerbaijan, were first homogenized through a  PET test and matched for age and class size, then randomly assigned to an AI-feedback group (20) or a teacher-feedback (control) group (20). Over seven 90-minute sessions (five weeks), each learner produced a 150–200-word argumentative essay per week. Both groups completed parallel pre- and post-test essays. Feedback was delivered within 48 hours of each writing submission, with AI feedback provided via Large Language Model (LLMs)’s standardized interface using ChatGPT and teacher feedback delivered by the trained instructor. Grammatical accuracy was operationalized as the number of errors per T-unit and scored independently by two trained raters. An ANCOVA controlling for pre-test performance revealed a significant main effect for feedback type. Post-test adjusted means showed that the teacher corrective feedback group outperformed the AI group. However, both groups from pre-test to post-test had an improvement in accuracy. However, this improvement in the group that received teacher corrective feedback was higher. As a result, in the Iranian context, teacher corrective feedback is more effective. Besides, these results advocate integrating AI tools into writing pedagogy to relieve teacher workload, provide immediate individualized input, and support data-driven instruction. Future research should test hybrid feedback models, track long-term retention, and explore learner perceptions across proficiency levels and institutional contexts.

Keywords

  • AI-assisted Corrective Feedback,
  • ChatGPT,
  • Grammatical Accuracy,
  • Iranian EFL Learners,
  • Teacher Corrective Feedback
PDF

References

  1. Atai, M. R., & Mazlum, F. (2013). English language-teaching curriculum in Iran: Planning and
  2. practice. The Curriculum Journal, 24(3), 389– 411. https://doi.org/10.1080/09585176.2012.744326
  3. Attal, A., Shvartz, S., Nakhoul , A.& Daniel Bahir, D.(2025). Chat GPT 4o vs residents: French
  4. language evaluation in ophthalmology. AJO International, 2, 34-45.
  5. Carla, M.M., Gambini, G., Baldascino, A. (2024).Large language models as assistance for
  6. glaucoma surgical cases: a ChatGPT vs. Google Gemini comparison. Graefe’s Archive for Clinical and Experimental Ophthalmol, 262(9), 2945–2959.
  7. Ellis, R. (2009). A typology of written corrective feedback types. ELT Journal, 63(2), 97–107.
  8. https://doi.org/10.1093/elt/ccn023
  9. Farhady, H., Sajadi Hezaveh, F., & Hedayati, H. (2010). Reflections on Foreign Language
  10. Education in Iran. The Electronic Journal for English as a Second Language, 13(4), 1-18.
  11. Hattie, J., & Timperley, H. (2007). The power of feedback. Review of Educational Research,
  12. 77(1), 81–112. https://doi.org/10.3102/003465430298487
  13. Hojatpanah, S., & , Dashtestani, R.(2020). Electronic Dictionaries as Language Learning Tools
  14. for Iranian Junior High School Students. Computer-Assisted Language Learning Electronic Journal, 21(1). 1-14.
  15. Hyland, K., & Hyland, F. (2019). Feedback in second language writing: Contexts and issues
  16. (2nd ed.). Cambridge University Press.
  17. Jordan, M. I. , & Mitchell, T. M.(2025). Machine learning: Trends, perspectives, and prospects.
  18. science, 349( 6245), 255-260. https://doi.org/ 10.1126/science.aaa8415
  19. Knoch, U. (2009). Diagnostic assessment of writing: A review of research and practice. Assessing Writing, 14(2), 112–129. https://doi.org/10.1016/j.asw.2009.04.001
  20. Li, S., Zhu, W., & Li, Y. (2022). The effects of different types of corrective feedback on L2
  21. writing. Language Teaching Research, 26(4), 715–738. https://doi.org/10.1177/1362168820926698
  22. Lin, SH., & Crosthwaite, P. (2024). The grass is not always greener: Teacher vs. GPT-assisted
  23. written corrective feedback. System, 127, 1-17.
  24. Luckin, R., & Holmes, W.(2016). Intelligence Unleashed: An argument for AI in Education.
  25. UCL Knowledge Lab.
  26. Lyster, R., & Saito, K. (2010). Oral Feedback in Classroom: SLA. Cambridge
  27. University Press
  28. Mulyono, H., & Halim, A. (2020). Developmental sequence analysis in Indonesian EFL writing:
  29. Implications for instruction. Indonesian Journal of Applied Linguistics, 10(1), 89–100. https://doi.org/10.17509/ijal.v10i1.25012
  30. Pishghadam, R. , Zabihi, R., & Kermanshahi, P.(2012). Educational Language Teaching: A New
  31. Movement beyond Reflective/Critical Teaching. Life Science Journal, 9 (1) 1, 892-899.
  32. Rahimi, M., & Mahboob, A. (2010). English as a foreign language in Iran: Challenges and
  33. prospects. Language Policy, 9(3), 231–249. https://doi.org/10.1007/s10993-010-9174-6
  34. Ranalli, J. (2021). Automated written corrective feedback: The role of metalinguistic
  35. information. Language Learning & Technology, 25(2), 44–61. https://www.lltjournal.org/item/10125-72717
  36. Sakai, D., Maeda, T., Ozaki, A., Kanda, G.N., Kurimoto, Y., Takahashi, M. (2023).Performance
  37. of ChatGPT in board examinations for specialists in the Japanese ophthalmology Society. Cureus, 20, 23-34. https://doi.org/10.7759/cureus.49903
  38. Selinker, L. (1972). Interlanguage . IRAL, 10, 209-231.
  39. Taghizadeh, M., & Yourdshahi, Z. (2020). Technology-enhanced feedback in EFL writing:
  40. Teachers’ and learners’ perspectives. System, 91, 102118. https://doi.org/10.1016/j.system.2020.102118
  41. Tao, B.K., Handzic, A., Hua, N.J., Vosoughi, A.R., Margolin, E.A., Micieli, J.A.(2024). Utility
  42. of ChatGPT for automated creation of patient education handouts: an application in Neuro-ophthalmology. Journal of Neuro-ophthalmol, 28, 11-23.
  43. Tuma, N.J., Caterini, J., Liblk, K. (2024). Performance of artificial intelligence on a simulated
  44. Canadian urology board exam. Canada Urological Association Journal, 18(10), 22-34. https://doi.org/ 10.5489/cuaj.8800. 26.
  45. Vaishya, R., Iyengar, K., Patralekh M. (2024).Effectiveness of AI-powered chatbots in
  46. responding to orthopaedic postgraduate exam questions—an observational study. International Orthopaedics, 48(8), 1963–1969. https://doi.org/10.1007/s00264-024-06182-9.
  47. Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes.
  48. Harvard University Press.
  49. Wang, SH., Wang, F.,& Zhu, Z.(2024). Artificial intelligence in education: A systematic
  50. literature review. Expert Systems with Applications, 252(4), 124-167. DOI: 10.1016/j.eswa.2024.124167
  51. Youn, CH., Salam, A. R., & Rahman, A.A. (2025). AI-Driven Tools in Providing Feedback on
  52. Studentʼs Writing. International Journal of Research and Innovation in Social Science, 9(3), 58-67.