International Journal of

ADVANCED AND APPLIED SCIENCES

EISSN: 2313-3724, Print ISSN: 2313-626X

Frequency: 12
line decor
  
line decor

 Volume 12, Issue 2 (February 2025), Pages: 205-214

----------------------------------------------

 Original Research Paper

Assessing the efficacy of ChatGPT's automated corrective feedback in enhancing students' writing proficiency

 Author(s): 

 Sultan M. Alanazi 1, Bilel Elmotri 2, 3, Gamal S. Khamis 1, Abdulbasit A. Darem 1, *

 Affiliation(s):

 1Department of Computer Science, Northern Border University, Arar, Saudi Arabia
 2Department of Languages and Translation, Applied College, Northern Border University, Arar, Saudi Arabia
 3Department of English Language, Faculty of Letters and Humanities, University of Sfax, Sfax, Tunisia

 Full text

  Full Text - PDF

 * Corresponding Author. 

  Corresponding author's ORCID profile: https://orcid.org/0000-0002-5650-1838

 Digital Object Identifier (DOI)

 https://doi.org/10.21833/ijaas.2025.02.022

 Abstract

The rise of large language models (LLMs) like ChatGPT has sparked interest in their educational applications. This study evaluates ChatGPT’s effectiveness in enhancing students’ writing skills through automated feedback. Using a mixed-methods design, pre-test assessments were conducted, followed by an intervention where the experimental group used ChatGPT for writing tasks, while the control group received traditional instruction. Post-test results showed that the ChatGPT group achieved greater improvements in writing performance, with higher average scores and percentage increases compared to the control group. Surveys and discussions revealed positive student perceptions of ChatGPT, highlighting its ease of use and constructive feedback, though concerns about data privacy, bias, and occasional irrelevant suggestions were noted. The findings suggest that ChatGPT can be a valuable educational tool for improving writing proficiency, but ethical considerations and individual differences in effectiveness must be addressed. Further research should explore its long-term impact, comparison with other automated systems, and applications in diverse learning contexts.

 © 2025 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords

 Writing proficiency, Automated feedback, Language models, Student perceptions, Educational tools

 Article history

 Received 16 September 2024, Received in revised form 18 January 2025, Accepted 7 February 2025

 Acknowledgment

The authors gratefully acknowledge the approval and the support of this research study by Grant No. SCIA-2023-12-2277 from the Deanship of Scientific Research at Northern Border University, Arar, K.S.A.

 Compliance with ethical standards

 Ethical considerations

Informed consent was obtained, data privacy ensured, and AI tool usage monitored for fairness. Risks were minimized, and participants received guidance on using AI feedback.

 Conflict of interest: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

 Citation:

 Alanazi SM, Elmotri B, Khamis GS, and Darem AA (2025). Assessing the efficacy of ChatGPT's automated corrective feedback in enhancing students' writing proficiency. International Journal of Advanced and Applied Sciences, 12(2): 205-214

 Permanent Link to this page

 Figures

 Fig. 1 

 Tables

 Table 1 Table 2 Table 3 Table 4 Table 5 

----------------------------------------------   

 References (18)

  1. Alkhaldi AA (2023). The impact of technology on students' creative writing: A case study in Jordan. Theory and Practice in Language Studies, 13(3): 586-592. https://doi.org/10.17507/tpls.1303.06   [Google Scholar]
  2. Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, and Agarwal S et al. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33: 1877-1901.   [Google Scholar]
  3. Chen X, Fang Y, Liu X, Zhao D, Feng X, and Li P (2019). Gender differences in latent classes of sleep quality in community-dwelling adults based on the Pittsburgh sleep quality index. Psychology, Health and Medicine, 24(8): 901-910. https://doi.org/10.1080/13548506.2019.1634825   [Google Scholar] PMid:31230460
  4. Gaud D (2023). Ethical considerations for the use of AI language model. International Journal for Research in Applied Science and Engineering Technology, 11(7): 6-14. https://doi.org/10.22214/ijraset.2023.54513   [Google Scholar]
  5. Geng J and Razali AB (2022). Effectiveness of the automated writing evaluation program on improving undergraduates' writing performance. English Language Teaching, 15(7): 49-60. https://doi.org/10.5539/elt.v15n7p49   [Google Scholar]
  6. Gozali I, Wijaya ART, Lie A, Cahyono BY, and Suryati N (2024). Leveraging the potential of ChatGPT as an automated writing evaluation (AWE) tool: Students' feedback literacy development and AWE tools integration framework. The JALT CALL Journal, 20(1): 1-22. https://doi.org/10.29140/jaltcall.v20n1.1200   [Google Scholar]
  7. Link S, Mehrzad M, and Rahimi M (2022). Impact of automated writing evaluation on teacher feedback, student revision, and writing improvement. Computer Assisted Language Learning, 35(4): 605-634. https://doi.org/10.1080/09588221.2020.1743323   [Google Scholar]
  8. Ma S, Chen Q, Wang X, Zheng C, Peng Z, Yin M, and Ma X (2024). Towards human-AI deliberation: Design and evaluation of LLM-empowered deliberative AI for AI-assisted decision-making. Arxiv Preprint Arxiv:2403.16812. https://doi.org/10.48550/arXiv.2403.16812   [Google Scholar]
  9. Mahapatra S (2024). Impact of ChatGPT on ESL students' academic writing skills: A mixed methods intervention study. Smart Learning Environments, 11: 9. https://doi.org/10.1186/s40561-024-00295-9   [Google Scholar]
  10. Mayer C, Wallner S, Budde-Spengler N, Braunert S, Arndt PA, and Kiefer M (2020). Literacy training of kindergarten children with pencil, keyboard or tablet stylus: The influence of the writing tool on reading and writing performance at the letter and word level. Frontiers in Psychology, 10: 3054. https://doi.org/10.3389/fpsyg.2019.03054   [Google Scholar] PMid:32038412 PMCid:PMC6987467
  11. Mohsen MA (2022). Computer-mediated corrective feedback to improve L2 writing skills: A meta-analysis. Journal of Educational Computing Research, 60(5): 1253-1276. https://doi.org/10.1177/07356331211064066   [Google Scholar]
  12. Montenegro-Rueda M, Fernández-Cerero J, Fernández-Batanero JM, and López-Meneses E (2023). Impact of the implementation of ChatGPT in education: A systematic review. Computers, 12(8): 153. https://doi.org/10.3390/computers12080153   [Google Scholar]
  13. Perkins M (2023). Academic integrity considerations of AI large language models in the post-pandemic era: ChatGPT and beyond. Journal of University Teaching and Learning Practice, 20(2): 07. https://doi.org/10.53761/1.20.02.07   [Google Scholar]
  14. Radford A, Wu J, Child R, Luan D, Amodei D, and Sutskever I (2019). Language models are unsupervised multitask learners. OpenAI Blog. Available online at: https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf 
  15. Song C and Song Y (2023). Enhancing academic writing skills and motivation: Assessing the efficacy of ChatGPT in AI-assisted language learning for EFL students. Frontiers in Psychology, 14: 1260843. https://doi.org/10.3389/fpsyg.2023.1260843   [Google Scholar] PMid:38162975 PMCid:PMC10754989
  16. Tarchi C, Zappoli A, Casado Ledesma L, and Brante EW (2024). The Use of ChatGPT in source-based writing tasks. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-024-00413-1   [Google Scholar]
  17. Zhong Y, Lian J, Huang H, and Deng H (2025). Affordances, constraints, and implications of ChatGPT in education from a social-ecological perspective: A data mining approach. Education and Information Technologies. https://doi.org/10.1007/s10639-024-13237-2   [Google Scholar]
  18. Zhuo TY, Huang Y, Chen C, and Xing Z (2023). Exploring AI ethics of ChatGPT: A diagnostic analysis. Arxiv Preprint Arxiv:2301.12867. https://doi.org/10.48550/arXiv.2301.12867   [Google Scholar]