Evaluative Voice and Interpersonal Shifts in ChatGPT-Translated Feedback for EFL Writing
DOI:
https://doi.org/10.17507/tpls.1606.11Keywords:
ChatGPT feedback, English-Arabic translation, interpersonal meaning, learner engagementAbstract
This study investigates how ChatGPT’s machine translation from English to Arabic affects the realization of interpersonal meaning and learner engagement in academic feedback for EFL learners. The main aim is to compare evaluative features in original and machine-translated feedback, addressing a significant gap in understanding the implications of AI-assisted translation for EFL writing pedagogy. Adopting qualitative comparative analysis, ChatGPT-generated English feedback and its Arabic translations were examined through the lenses of Appraisal Theory by Martin and White (2005) and Hyland’s (2006) Reader Engagement Model. The findings reveal that in the Arabic translations the authorial voice shifts to be more distant and directive, often resulting in more instructional but less empathetic feedback. The study concludes that while ChatGPT feedback has potential, human oversight is essential to maintain interpersonal depth, learner engagement, supportive and personalized characteristics crucial for effective feedback in EFL contexts. Future research is recommended to explore EFL learner perceptions of translated feedback and to develop strategies for achieving the full pedagogical potential of AI-assisted feedback translation.
References
Abbamonte, L., & Cavaliere, F. (2006). Lost in translation: The Italian rendering of UNICEF “The State of the World’s Children 2004” report. In M. Gotti & S. Šarčević (Eds.), Insights into specialized translation (pp. 235-258). Berg: Peter Lang.
Alkhawaja, L. (2024). Unveiling the New Frontier: ChatGPT-3 Powered Translation for Arabic-English Language Pairs. Theory and Practice in Language Studies, 14(2), 347-357. https://doi.org/10.17507/tpls.1402.05
Alshehri, M. (2025). Integrating Automated Writing Evaluation into Saudi EFL Students’ Writing Practice. Arab World English Journal, 16(1), 70-87. https://doi.org/10.24093/awej/vol16no1.5
Alshehri, A., Alshehri, E., & Aljamal, N. (2025). Appraisal Theory Tagger [Computer software]. S. A. F. I. Property. Retrieved April 18, 2025, from https://appraisal-tagger.netlify.app/
Al-Shunnag, M. (2014). Stance in political discourse: Arabic translations of American newspaper opinion articles on the ‘Arab Spring’ [Unpublished doctoral dissertation, University of Salford].
Alsofyani, A. H., & Barzanji, A. M. (2024). The Effects of ChatGPT-Generated Feedback on Saudi EFL Learners’ Writing Skills and Perception at the Tertiary Level: A Mixed-Methods Study. Journal of Educational Computing Research, 63(2), 431-463. https://doi.org/10.1177/07356331241307297
Awidi, I. T. (2024). Comparing expert tutor evaluation of reflective essays with marking by generative artificial intelligence (AI) tool. Computers and Education: Artificial Intelligence, 6, 100226. https://doi.org/10.1016/j.caeai.2024.100226
Banihashem, S. K., Kerman, N. T., Noroozi, O., Moon, J., & Drachsler, H. (2024). Feedback sources in essay writing: peer-generated or AI-generated feedback? International Journal of Educational Technology in Higher Education, 21(1). https://doi.org/10.1186/s41239-024-00455-4
Cao, S., & Zhong, L. (2023). Exploring the effectiveness of ChatGPT-based feedback compared with teacher feedback and self-feedback: Evidence from Chinese to English translation. arXiv.org. https://doi.org/10.48550/ARXIV.2309.01645
Carless, D. (2022). From teacher transmission of information to student feedback literacy: Activating the learner role in feedback processes. Active Learning in Higher Education, 23(2), 143–153.
Dai, W., Tsai, Y.-S., Lin, J., Aldino, A., Jin, H., Li, T., Gašević, D., & Chen, G. (2024). Assessing the proficiency of large language models in automatic feedback generation: An evaluation study. Computers and Education: Artificial Intelligence, 7, 100299. https://doi.org/10.1016/j.caeai.2024.100299
Hyland, K. (2006). Representing readers in writing: Student and expert practices. Linguistics and Education, 16, 363–377.
Hyland, K., & Jiang, F. (2016). “We must conclude that…”: A diachronic study of academic engagement. Journal of English for Academic Purposes, 24, 29–42.
Hwang, S. (2025). Unpacking the Impact of Writing Feedback Perception on Self-Regulated Writing Ability: The Role of Writing Self-Efficacy and Self-Regulated Learning Strategies. Behavioral Sciences, 15(2), 100. https://doi.org/10.3390/bs15020100
Khondaker, M. T. I., Waheed, A., Nagoudi, E. M. B., & Abdul-Mageed, M. (2023). GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP. arXiv.org. https://doi.org/10.48550/ARXIV.2305.14976
Li, X., Meng, Y., & Jing, Y. (2025). An Appraisal-based Study on Divergence of Evaluative Meanings in Student Translations. WORD, 71(2), 97-113. https://doi.org/10.1080/00437956.2025.2499341
Lin, S., & Crosthwaite, P. (2024). The grass is not always greener: Teacher vs. GPT-assisted written corrective feedback. System, 127, 103529. https://doi.org/10.1016/j.system.2024.103529
Martin, J., & White, P. (2005). The language of evaluation: Appraisal in English. Palgrave Macmillan.
Mohsen, M. (2024). Artificial Intelligence in Academic Translation: A Comparative Study of Large Language Models and Google Translate. Psycholinguistics, 35(2), 134-156. https://doi.org/10.31470/2309-1797-2024-35-2-134-156
Munday, J. (2009). The concept of the interpersonal in translation. SYNAPS, 23, 1527. Retrieved June 21, 2025, from http://hdl.handle.net/11250/2406113
Qian, H. (2017). Investigating “Unfaithful” Translations via the Appraisal Theory: A Case Study of Public Notices. Arab World English Journal for Translation & Literary Studies, 1(1). http://doi.org/10.24093/awejtls/vol1no1.13
Rad, H. S., Alipour, R., & Jafarpour, A. (2024). Using artificial intelligence to foster students’ writing feedback literacy, engagement, and outcome: A case of Wordtune application. Interactive Learning Environments, 32(9), 5020–5040.
Rosa, A. A. (2013). The power of voice in translated fiction: Or, following a linguistic track in translation studies. In C. Way, S. Vandepitte, R. Meylaerts, & M. Bartłomiejczyk (Eds.), Tracks and treks in translation studies. Amsterdam: John Benjamins Publishing Company.
Sardinha, T. B. (2024). AI-generated vs human-authored texts: A multidimensional comparison. Applied Corpus Linguistics, 4(1), 100083. https://doi.org/10.1016/j.acorp.2023.100083
Steiss, J., Tate, T., Graham, S., Cruz, J., Hebert, M., Wang, J., Moon, Y., Tseng, W., Warschauer, M., & Olson, C. B. (2024). Comparing the quality of human and ChatGPT feedback of students’ writing. Learning and Instruction, 91, 101894. https://doi.org/10.1016/j.learninstruc.2024.101894
Sun, Y. (2021). The effect of teacher caring behavior and teacher praise on students’ engagement in EFL classrooms. Frontiers in psychology, 12, 746871. https://doi.org/10.3389/fpsyg.2021.746871
Tajvidi, G.-R., & Arjani, S. H. (2017). Appraisal Theory in Translation Studies: An Introduction and Review of Studies of Evaluation in Translation. Journal of Research in Applied Linguistics, 8(2), 3-30.
Zhang, M. (2013). Stance and mediation in transediting news headlines as paratexts. Perspectives, 21(3), 396-411.
Zou, S., Guo, K., Wang, J., & Liu, Y. (2024). Investigating students’ uptake of teacher-and ChatGPT-generated feedback in EFL writing: a comparison study. Computer Assisted Language Learning, 1-30. https://doi.org/10.1080/09588221.2024.2447279
