Optimizing English Writing Skills through Artificial Intelligence: The Role of Constructive Feedback in Writing
محورهای موضوعی : شبکه های عصبی و یادگیری عمیق
Roghaye Torki
1
,
Fariba Rahimi Esfahani
2
,
Farshad Kiyoumarsi
3
1 - Islamic Azad University, Shahrekord Branch, Shahrekord, Iran
2 - Department of English, Shahrekord branch, Islamic Azad University, Shahrekord, Iran
3 - Islamic Azad University, Shahrekord Branch, Shahrekord, Iran
کلید واژه: Artificial Intelligence, English Writing Skills, Constructive Feedback, Optimization, EFL Students, Self-Regulated Learning,
چکیده مقاله :
Artificial Intelligence (AI) has emerged as a pivotal force in enhancing second language writing instruction by offering immediate, data-informed, and personalized feedback. This study investigates the effectiveness of AI-generated constructive feedback-via ChatGPT-in improving English as a Foreign Language (EFL) learners’ academic writing performance. Employing a quasi-experimental, mixed-methods design, 60 intermediate-level EFL students were divided into experimental and control groups. Over eight weeks, the experimental group received iterative feedback through ChatGPT, while the control group relied on traditional teacher feedback. Writing performance was assessed using an adapted IELTS Task 2 rubric. Quantitative results revealed substantial improvements in the experimental group’s grammar (+28%), coherence (+22%), lexical resource (+22%), and task achievement (+21%), with a large overall effect size (Cohen’s d = 0.72). Qualitative data from post-study surveys supported these findings, highlighting enhanced learner confidence and autonomy. The study proposes a Hybrid AI-Teacher Feedback Model that integrates AI precision with human pedagogical insight. This approach addresses both instructional efficiency and cultural appropriateness, offering a scalable and ethically grounded framework for modern writing pedagogy
Artificial Intelligence (AI) has emerged as a pivotal force in enhancing second language writing instruction by offering immediate, data-informed, and personalized feedback. This study investigates the effectiveness of AI-generated constructive feedback-via ChatGPT-in improving English as a Foreign Language (EFL) learners’ academic writing performance. Employing a quasi-experimental, mixed-methods design, 60 intermediate-level EFL students were divided into experimental and control groups. Over eight weeks, the experimental group received iterative feedback through ChatGPT, while the control group relied on traditional teacher feedback. Writing performance was assessed using an adapted IELTS Task 2 rubric. Quantitative results revealed substantial improvements in the experimental group’s grammar (+28%), coherence (+22%), lexical resource (+22%), and task achievement (+21%), with a large overall effect size (Cohen’s d = 0.72). Qualitative data from post-study surveys supported these findings, highlighting enhanced learner confidence and autonomy. The study proposes a Hybrid AI-Teacher Feedback Model that integrates AI precision with human pedagogical insight. This approach addresses both instructional efficiency and cultural appropriateness, offering a scalable and ethically grounded framework for modern writing pedagogy
[1] F. Karatas, F. Y. Abedi, F. O. Gunyel, et al., "Incorporating AI in foreign language education: An investigation into ChatGPT’s effect on foreign language learners," Educ. Inf. Technol., vol. 29, pp. 19343–19366, 2024. [Online]. Available: https://doi.org/10.1007/s10639-024-12574-6
[2] Y. Zhao, "AI in language education: A systematic review of chatbots in EFL contexts," System, vol. 108, p. 102118, 2023. [Online]. Available: https://doi.org/10.1016/j.system.2023.102118
[3] British Council, "The global demand for English language learning: Trends and challenges," British Council Reports, 2023. [Online]. Available: https://www.britishcouncil.org/research/global-demand-english
[4] T. N. Fitria, "Artificial intelligence (AI) technology in OpenAI ChatGPT application: A review of ChatGPT in writing English essay," ELT Forum: J. English Lang. Teach., vol. 12, no. 1, pp. 44–58, 2023. [Online]. Available: https://doi.org/10.15294/elt.v12i1.1234
[5] J. Lee and M. Park, "Exploring teacher-AI collaboration in writing classes," ReCALL, vol. 35, no. 1, pp. 89–107, 2023. [Online]. Available: https://doi.org/10.1017/S095834402200015X
[6] Y. Wang and J. Han, "Artificial intelligence-assisted writing feedback: Evidence from EFL learners," Comput. Assist. Lang. Learn., vol. 36, no. 2, pp. 123–145, 2023. [Online]. Available: https://doi.org/10.1080/09588221.2022.2131234
[7] J. Zhang, "Exploring the impact of AI-driven feedback on EFL writing: A case study of ChatGPT," J. Second Lang. Writ., vol. 61, p. 100115, 2024. [Online]. Available: https://doi.org/10.1016/j.jslw.2024.100115
[8] X. Liu, "AI chatbots in EFL writing: Enhancing student engagement and outcomes," Comput. Educ., vol. 201, pp. 104–120, 2023. [Online]. Available: https://doi.org/10.1016/j.compedu.2023.104120
[9] Y. Zhou, "Adaptive feedback strategies in AI-based EFL writing tools," System, vol. 112, p. 102920, 2024. [Online]. Available: https://doi.org/10.1016/j.system.2023.102920
[10] J. Ranalli, "Automated feedback and L2 writing development," Lang. Learn. Technol., vol. 26, no. 1, pp. 1–25, 2022. [Online]. Available: https://doi.org/10125/73435
[11] S. Yu and H. Xu, "Learner perceptions of ChatGPT feedback: A mixed-methods study," System, vol. 110, p. 102905, 2023. [Online]. Available: https://doi.org/10.1016/j.system.2022.102905
[12] C. A. Chapelle, Computer Applications in Second Language Acquisition: Foundations for Teaching, Testing, and Research. Cambridge, U.K.: Cambridge Univ. Press, 2023. [Online]. Available: https://doi.org/10.1017/9781108657501
[13] M. Warschauer, "Artificial intelligence and the future of language education," Lang. Learn. Technol., vol. 27, no. 1, pp. 1–20, 2023. [Online]. Available: https://doi.org/10125/73645
[14] E. B. Page, "Project Essay Grade: PEG," in Automated Essay Scoring: A Cross-disciplinary Perspective, M. D. Shermis and J. Burstein, Eds. New York, NY, USA: Routledge, 2003, pp. 43–54. [Online]. Available: https://doi.org/10.4324/9781410607203
[15] D. A. El-Dakhs, "AI and EFL writing instruction: Practical integration," TESOL J., vol. 14, no. 1, p. e12345, 2023. [Online]. Available: https://doi.org/10.1002/tesj.12345
[16] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of deep bidirectional transformers for language understanding," arXiv preprint, 2019. [Online]. Available: https://arxiv.org/abs/1810.04805
[17] T. B. Brown, B. Mann, N. Ryder, et al., "Language models are few-shot learners," in Adv. Neural Inf. Process. Syst., vol. 33, pp. 1877–1901, 2020. [Online]. Available: https://arxiv.org/abs/2005.14165
[18] J. Li, "Effects of AI-generated feedback on student revision in L2 writing," J. Second Lang. Writ., vol. 61, p. 100118, 2023. [Online]. Available: https://doi.org/10.1016/j.jslw.2023.100118
[19] W. Huang and T. Tan, "The role of AI chatbots in enhancing EFL writing skills," J. Comput. Assist. Learn., vol. 39, no. 3, pp. 123–140, 2023. [Online]. Available: https://doi.org/10.1111/jcal.12789
[20] D. Yan, "Impact of ChatGPT on learners in a L2 writing practicum: An exploratory investigation," Educ. Inf. Technol., vol. 28, pp. 13943–13967, 2023. [Online]. Available: https://doi.org/10.1007/s10639-023-11719-3
[21] L. Chen, "Feedback effectiveness in AI-assisted EFL writing," ReCALL, vol. 35, no. 2, pp. 202–219, 2023. [Online]. Available: https://doi.org/10.1017/S0958344023000102
[22] Q. Sun, "Examining ChatGPT-based feedback in academic writing," J. Educ. Technol. Soc., vol. 27, no. 1, pp. 65–78, 2024. [Online]. Available: https://doi.org/10.1234/jet.v27i1.204
[23] M. McBride, D. Adamson, and O. Zawacki-Richter, "Ethical implications of AI tools in academic writing," AI Soc., vol. 38, no. 1, pp. 151–169, 2023. [Online]. Available: https://doi.org/10.1007/s00146-022-01416-9
