The effect of artificial intelligence mediated feedback on english language learners' writing ability
DOI:
https://doi.org/10.62452/g6023m93Palavras-chave:
Ai-mediated feedback, writing ability, EFL learners, perceptions, accuracy, coherenceResumo
This study investigated the impact of AI-mediated feedback on the writing skills of Iranian intermediate EFL learners, with a focus on accuracy, coherence, and cohesion, as well as learners’ perceptions of the benefits and challenges associated with AI in the writing process. Sixty female EFL learners, aged 15 to 20, were purposively selected from a private language institute and divided into two groups: one receiving AI-mediated feedback via the Poe Application, and the other receiving traditional teacher feedback. Writing proficiency was assessed using IELTS Writing Task 2, administered as both pre- and post-tests. The results indicated that learners who received AI-mediated feedback demonstrated significant improvements in grammatical accuracy, coherence, and cohesion compared to those who received traditional feedback. Qualitative data, collected through semi-structured interviews with a subset of the experimental group, revealed that learners appreciated the immediacy, personalization, and accessibility of AI feedback, which enhanced their motivation and supported autonomous learning. However, participants also expressed concerns regarding the lack of human connection, potential over-reliance on AI, and the limitations of AI in understanding contextual nuances. These findings suggest that while AI-mediated feedback is effective in improving key aspects of EFL writing, it is most beneficial when integrated with human guidance.
Downloads
Referências
Aminovna, B. D. (2022). Importance of coherence and cohesion in writing. Eurasian Research Bulletin, 4, 83–89. https://geniusjournals.org/index.php/erb/article/view/431
Bahaziq, A. (2016). Cohesive devices in written discourse: A discourse analysis of a student’s essay writing. English Language Teaching, 9(7), 112–112. https://doi.org/10.5539/elt.v9n7p112
Barrot, J. S. (2023). Using automated written corrective feedback in the writing classrooms: Effects on L2 writing accuracy. Computer Assisted Language Learning, 36(4), 584–607. https://doi.org/10.1080/09588221.2021.1936071
Borna, P., Mohammadi, R., & Karimi Nia, R. (2024). Investigating the effect of AI writing assistance tools on Iranian intermediate EFL learners' writing performance: A comparative study of ProWritingAid and Grammarly. Research in English Language Pedagogy, 12(3), 478–504. https://doi.org/10.30486/RELP.2024.897162
Chávez-Cárdenas, M. d. C., Fernández-Marín, M. Á., & Lamí-Rodríguez del Rey, L. E. (2025). Web educativa e inteligencia artificial: Transformando el aprendizaje contemporáneo. Sophia Editions.
Chen, X., Xie, H., Zou, D., & Hwang, G.-J. (2020). Application and theory gaps during the rise of artificial intelligence in education. Computers and Education: Artificial Intelligence, 1, Article 100002. https://doi.org/10.1016/j.caeai.2020.100002
Diebold, G. (2023). Higher education will have to adapt to generative AI—And that’s a good thing. Center for Data Innovation. https://datainnovation.org/2023/01/higher-education-will-have-to-adapt-to-generative-ai-and-thats-a-good-thing/
Ellis, R. (2010). A framework for investigating oral and written corrective feedback. EPILOGUE. Studies in Second Language Acquisition, 32(2), 335–349. https://doi.org/10.1017/s0272263109990544
Fathi, J., & Rahimi, M. (2024). Utilising artificial intelligence-enhanced writing mediation to develop academic writing skills in EFL learners: A qualitative study. Computer Assisted Language Learning, 1–20. https://doi.org/10.1080/09588221.2024.2374772
Ghorbandordinejad, F., & Kenshinbay, T. (2024). Exploring AI-driven adaptive feedback in the second language writing skills prompt. AI Technology in Language Teaching, 2(3), 1–13. https://doi.org/10.59652/jetm.v2i3.264
Hyland, K., & Hyland, F. (2006). Feedback on second language students’ writing. Language Teaching, 39(2), 83–101. https://doi.org/10.1017/S0261444806003399
Jafarian, K., Soori, F., & Kafipour, K. (2012). The effect of computer assisted language learning (CALL) on EFL high school students' writing achievement. European Journal of Social Sciences, 27(2), 138–148.
Jasim, M. Y., Musa, Z. H., Asim, Z. A., & Salman, A. R. (2024). Developing EFL writing with AI: Balancing benefits and challenges. Technology Assisted Language Education, 2(2), 80-93. https://doi.org/10.22126/TALE.2024.10953.1052
Jawas, U. (2019). Writing anxiety among Indonesian EFL students: Factors and strategies. International Journal of Instruction, 12(4), 733–746. https://files.eric.ed.gov/fulltext/EJ1230040.pdf
Lee, I. (2019). Teacher written corrective feedback: Less is more. Language Teaching, 52(4), 524–536. https://doi.org/10.1017/s0261444819000247
León-González, J. L., & Pire-Rojas, A. (Comp). (2025). Investigación, neurociencia e inteligencia artificial: Hacia una formación universitaria integral. Sophia Editions.
Marzuki, W., Rusdin, D., Darwin, W., & Indrawati, I. (2023). The impact of AI writing tools on the content and organization of students' writing: EFL teachers' perspective. Cogent Education, 10(2). https://doi.org/10.1080/2331186X.2023.2236469
Sanosi, A. B. (2022). The impact of automated written corrective feedback on EFL learners’ academic writing accuracy. The Journal of Teaching English for Specific and Academic Purposes, 10(2), 301–317. https://doi.org/10.22190/JTESAP2202301S
Wang, D. (2024). Teacher-versus AI-generated (POE application) corrective feedback and language learners’ writing anxiety, complexity, fluency, and accuracy. International Review of Research in Open and Distributed Learning, 25(3), 37–56. https://doi.org/10.19173/irrodl.v25i3.7646
Wang, Z., & Han, F. (2022). The effects of teacher feedback and automated feedback on cognitive and psychological aspects of foreign language writing: A mixed-methods research. Frontiers in Psychology, 13, 909802. https://doi.org/10.3389/fpsyg.2022.909802
Weigle, R. (2002). Focus on the global essay: A schematic approach to improving TOEFL writing. Cambridge University Press.
Zeevy-Solovey, O. (2024). Comparing peer, ChatGPT, and teacher corrective feedback in EFL writing: Students’ perceptions and preferences. Technology in Language Teaching & Learning, 6(3), 1–23. https://doi.org/10.29140/tltl.v6n3.1482
Downloads
Publicado
Edição
Seção
Licença
Copyright (c) 2025 Zeinab Elghani, Nafiseh Asadzadeh-Maleki (Autor/a)
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Os autores que publicam na Revista Metropolitana de Ciencias Aplicadas (REMCA), concordam com os seguintes termos:
1. Direitos autorais
Os autores mantêm direitos autorais irrestritos sobre suas obras. Os autores concedem ao periódico o direito de primeira publicação. Para tal, cedem à revista, em caráter não exclusivo, direitos de exploração (reprodução, distribuição, comunicação pública e transformação). Os autores podem firmar acordos adicionais para a distribuição não exclusiva da versão publicada do trabalho no periódico, desde que haja reconhecimento de sua publicação inicial nesta revista.
© Os autores.
2. Licença
Os trabalhos são publicados na revista sob a licença Creative Commons Atribuição-NãoComercial-CompartilhaIgual 4.0 Internacional (CC BY-NC-SA 4.0). Os termos podem ser encontrados em: https://creativecommons.org/licenses/by-nc-sa/4.0/deed.pt
Esta licença permite:
- Compartilhar: copiar e redistribuir o material em qualquer meio ou formato.
- Adaptar: remixar, transformar e desenvolver o material.
Nos seguintes termos:
- Atribuição: Você deve dar o crédito apropriado, fornecer um link para a licença e indicar se alguma alteração foi feita. Você pode fazer isso de qualquer maneira razoável, mas não de uma forma que sugira que o licenciante endossa ou patrocina seu uso.
- Não comercial: você não pode usar o material para fins comerciais.
- Compartilhamento pela mesma licença: se você remixar, transformar ou criar a partir do material, deverá distribuir sua criação sob a mesma licença do trabalho original.
Não há restrições adicionais. Você não pode aplicar termos legais ou medidas tecnológicas que restrinjam legalmente outros de fazerem qualquer coisa que a licença permita.
