Effectiveness of Accurate ChatGPT Commands in Enhancing A2 Level Academic Writing Feedback

Authors

  • Jhomayra Isabel Hoyos Valdiviezo

    Educational Science Department, Universidad Técnica Estatal de Quevedo, Quevedo 120301, Ecuador
  • Jardel Coutinho dos Santos

    Educational Science Department, Universidad Técnica Estatal de Quevedo, Quevedo 120301, Ecuador
  • Rafaela María Vinueza Beltrán

    Educational Science Department, Universidad Yachay Tech, Urcuqui 100115, Ecuador

DOI:

https://doi.org/10.30564/fls.v7i12.11647
Received: 14 August 2025 | Revised: 25 August 2025 | Accepted: 11 September 2025 | Published Online: 3 November 2025

Abstract

Academic writing presents significant challenges for beginner learners of English as a Foreign Language (EFL), where learners tend to make mistakes in grammar, coherence, and structure. Feedback is essential for the development of writing, yet in traditional instructional models it is not always provided with the quality or frequency required. This study explores the effectiveness of ChatGPT-generated feedback in enhancing academic writing skills among A2-level English as a Foreign Language learners. Involving a pre-post experimental design, 45 students participated over a fourteen-week intervention period within two groups: one receiving traditional instruction and the other using ChatGPT guided by a tailored prompt created by the principal researcher: "Evaluate this paragraph based on Cambridge A2-level standards  (CEFR) for Content, Organization, and Language (vocabulary and grammar). Provide specific feedback". The results showed statistically significant gains in writing performance for the experimental group, especially in language accuracy and structural organization, with no regression in any skill area, confirming that AI feedback has the potential to facilitate language acquisition among participants at a beginner level, without compromising learner autonomy, when conducted through a structured approach. The research indicates that ChatGPT can be utilized as a pedagogical tool in addition to regular education, serving as a scalable resource with the aid of clear evaluative criteria. Future research is encouraged to expand this approach to other CEFR proficiency levels and explore learners' qualitative experiences with AI feedback.

Highlights

  • The first quasi-experimental study used structured ChatGPT prompts to improve A2-level academic writing in EFL settings.
  • Inter-rater reliability validates the statistically significant increases in grammar, vocabulary, and organization demonstrated.
  • Provide a feasible 12-week intervention framework that teachers can incorporate into their weekly lesson plans.
  • Emphasize the balance between AI feedback and human mediation, supporting the pedagogical foundation.
  • Provides implications for extending AI-assisted feedback across multiple CEFR competency levels and investigating cognitive processes involved in L2 writing

Keywords:

AI; Academic Writing; ChatGPT; CEFR; EFL; Feedback; Prompt; Writing

References

[1] Pasaribu, A.N., Pasaribu, T.K., Siahaan, R.B., et al., 2024. Challenges for Indonesian EFL students in English academic writing. English Review: Journal of English Education. 12(2), 527–536. DOI: https://doi.org/10.25134/erjee.v12i2.9780

[2] Mahmood, K., 2021. Academic writing challenges of EFL learners and teachers’ proficiency in Pakistani higher education. Journal of Research in Social Sciences. 8(2), 56–57. DOI: https://doi.org/10.52015/jrss.8i2.55

[3] Song, C., 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. DOI: https://doi.org/10.3389/fpsyg.2023.1260843

[4] Alostath, K., 2021. Teachers’ perception of EFL students’ poor writing skills: The challenges, causes, and remedies. International Journal of Science Research (Raipur). 10(4), 647–651. DOI: https://doi.org/10.21275/sr21413012657

[5] Zhou, T., Cao, S., Zhou, S., et al., 2023. Chinese intermediate English learners outdid ChatGPT in deep cohesion: Evidence from English narrative writing. System. 118, 103141. DOI: https://doi.org/10.1016/j.system.2023.103141

[6] Liu, G., Ma, C., 2024. Measuring EFL learners’ use of ChatGPT in informal digital learning of English based on the technology acceptance model. Innovation in Language Learning and Teaching. 18(2), 125–138. DOI: https://doi.org/10.1080/17501229.2023.2240316

[7] Ibrahim, K., Kirkpatrick, R., 2024. Potentials and implications of ChatGPT for ESL writing instruction. International Review of Research in Open and Distributed Learning. 25(3), 394–409. DOI: https://doi.org/10.19173/irrodl.v25i3.7820

[8] Krause, S., Panchal, B.H., Ubhe, N., 2025. The evolution of learning: Assessing the transformative impact of generative AI on higher education. In: Lecture Notes on Data Engineering and Communications Technologies. Springer Nature: Singapore. pp. 356–371. DOI: https://doi.org/10.1007/s44366-025-0058-7

[9] Polakova, P., Ivenz, P., 2024. The impact of ChatGPT feedback on the development of EFL students’ writing skills. Cogent Education. 11(1). DOI: https://doi.org/10.1080/2331186X.2024.2410101

[10] Ng, D.T.K., Tan, C.W., Leung, J.K.L., 2024. Empowering student self‐regulated learning and science education through ChatGPT: A pioneering pilot study. British Journal of Educational Technology. 55(4), 1328–1353. DOI: https://doi.org/10.1111/bjet.13454

[11] Theophilou, E., Koyutürk, C., Yavari, M., et al., 2023. Learning to prompt in the classroom to understand AI limits: A pilot study. In Proceedings of the AIxIA 2023 – Advances in Artificial Intelligence: XXIInd International Conference of the Italian Association for Artificial Intelligence, AIxIA 2023, Rome, Italy, 6–9 November 2023. DOI: https://doi.org/10.1007/978-3-031-47546-7_33

[12] Kusuma, I., Roni, M., Dewi, K., et al., 2024. Revealing the potential of ChatGPT for English language teaching: EFL preservice teachers’ teaching practicum experience. Studies in English Language and Education. 11(2), 650–670. DOI: https://doi.org/10.24815/siele.v11i2.34748

[13] Tseng, Y.C., Lin, Y.H., 2024. Enhancing English as a Foreign Language (EFL) learners’ writing with ChatGPT: A university-level course design. Electronic Journal of E-Learning. 22(2), 78–97. DOI: https://doi.org/10.34190/ejel.21.5.3329

[14] Xiao, F., Zhu, S., Xin, W., 2025. Exploring the landscape of generative AI (ChatGPT)-powered writing instruction in English as a Foreign Language education: A scoping review. ECNU Review of Education. 1–19. DOI: https://doi.org/10.1177/20965311241310881

[15] Li, J., Huang, J., Wu, W., et al., 2024. Evaluating the role of ChatGPT in enhancing EFL writing assessments in classroom settings: A preliminary investigation. Humanities and Social Sciences Communications. 11(1). DOI: https://doi.org/10.1057/s41599-024-03755-2

[16] Nguyen, A., Duong, A.T., Nguyen, D.T.B., et al., 2025. Guidelines for learning design and assessment for generative artificial intelligence-integrated education: A unified view. Information and Learning Sciences. ahead-of-print. DOI: https://doi.org/10.1108/ils-11-2024-0148

[17] Alghannam, M.S.M., 2024. Artificial intelligence as a provider of feedback on EFL student compositions. World Journal of English Language. 15(2), 161. DOI: https://doi.org/10.5430/wjel.v15n2p161

[18] Duc, A.N., Lønnestad, T., Sundbø, I., et al., 2023. Generative AI in undergraduate information technology education – Insights from nine courses. arXiv. arXiv:2311.10199. DOI: https://doi.org/10.48550/arXiv.2311.10199

[19] Tesch, A., 2016. Implementing pre‐post test designs in higher education evaluations. New Directions for Evaluation. 2016(151), 85–96. DOI: https://doi.org/10.1002/ev.20195

[20] Jacobsen, L., Weber, K., 2025. The promises and pitfalls of LLMs as feedback providers: A study of prompt engineering and the quality of AI-driven feedback. OSF Preprints. DOI: https://doi.org/10.31219/osf.io/cr257

[21] Cambridge Assessment English, 2024. Teacher guide for writing A2 Key for Schools. Available from: https://www.cambridgeenglish.org/Images/600973-teacher-guide-for-writing-a2-key-for-schools.pdf (cited 5 December 2024).

[22] Landis, J.R., Koch, G.G., 1977. The measurement of observer agreement for categorical data. Biometrics. 33(1), 159–174. DOI: https://doi.org/10.2307/2529310

[23] Field, A., 2024. Discovering Statistics Using IBM SPSS Statistics, 6th ed. SAGE Publications: London, UK.

[24] Hoyos Valdiviezo, I., 2025. Dataset: ChatGPT feedback interventions for A2-level EFL academic writing. Available from: https://doi.org/10.6084/m9.figshare.29755598.v1 (cited 10 August 2025).

[25] Teng, M.F., Huang, J., 2025. Incorporating ChatGPT for EFL writing and its effects on writing engagement. International Journal of Computer-Assisted Language Learning and Teaching. 15(1), 1–21. DOI: https://doi.org/10.4018/ijcallt.367874

[26] Huang, J., 2023. Engineering ChatGPT prompts for EFL writing classes. International Journal of TESOL Studies. 5(4), 73–79. DOI: https://doi.org/10.58304/ijts.20230405

[27] Gozali, I., Wijaya, A.R.T., Lie, A., et al., 2024. Leveraging the potential of ChatGPT as an automated writing evaluation (AWE) tool: Students’ feedback literacy development and AWE tools integration framework. JALT CALL Journal. 20(1), 1–22. DOI: https://doi.org/10.29140/jaltcall.v20n1.1200

Downloads

How to Cite

Hoyos Valdiviezo, J. I., dos Santos, J. C., & Vinueza Beltrán, R. M. (2025). Effectiveness of Accurate ChatGPT Commands in Enhancing A2 Level Academic Writing Feedback. Forum for Linguistic Studies, 7(12), 12–25. https://doi.org/10.30564/fls.v7i12.11647

Issue

Vol. 7 , Iss. 12 (December 2025): In progress

Article Type

Article

License

Copyright © 2025 Jhomayra Isabel Hoyos Valdiviezo, Jardel Coutinho dos Santos, Rafaela María Vinueza Beltrán

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.