The Effect of Data-Driven Feedback, AI-Assisted Error Analysis, and Translation Knowledge on Trainee Translators’ Performance

Amina AlBenghazi; Naeimah Ali

doi:10.36602/faj.2026.n21.19

Authors

Amina AlBenghazi University of Tripoli, Faculty of literature and Languages, Department of English, Libya
Naeimah AlSuwee Ali University of Tripoli, Faculty of literature and Languages, Department of Translation, Libya

DOI :

https://doi.org/10.36602/faj.2026.n21.19

Keywords:

data-driven feedback, trainee students, performance, AI-empowered tools, METEOR assessment

Abstract

Feedback plays a pivotal role in enhancing learning outcomes in education; however, the integration of artificial intelligence-generated feedback, particularly that produced by advanced language models such as ChatGPT, remains largely underexplored within the field of translation teaching. This research investigates the impact of data-driven feedback strategies on the performance of 70 trainee translators recruited from administrative and economic workshops in The Translation Department at Tripoli University. Participants were chosen based on specific criteria, and all received theoretical knowledge and training on English-Arabic translation; moreover, all completed the pre-requisite translation workshop courses. It also explores the influence of AI tools and their support in analyzing translation. Data was collected by conducting pre- and post-tests and adopting a training program based on cooperative learning. ChatGPT-4 was used to analyze the translations and identify errors. Translation quality was evaluated using the automatic metric "METEOR. "The results of the tests show improvements in trainees' performance. The adopted strategies allow instructors to achieve the goals and track the trainees' progress by addressing the challenges when they appear and providing immediate feedback with reliance on cooperative learning, ChatGPT 4 text analysis, and automatic assessment. The approach has a positive impact on the evaluation and feedback process. Based on the test results, the tools can be adopted as a pedagogical resource to provide initial reflections on translation work and its effectiveness when combined with human reinforcement.

Author Biographies

Amina AlBenghazi , University of Tripoli, Faculty of literature and Languages, Department of English, Libya

Amina Al Benghazi is a Libyan academic with a solid background in education and translation. She holds a Bachelor's Degree in Translation Studies and a Master's Degree in English Linguistics from Tripoli University, Libya. She worked as a translator at the Sunni Office for Legal Translation and at the Al Massar company for Studying Abroad. Additionally, she served as an English teacher in international schools and at the NRC organisation for refugees. Currently, I work as a lecturer at the University of Refaq.

Naeimah AlSuwee Ali , University of Tripoli, Faculty of literature and Languages, Department of Translation, Libya

Dr Naeimah Sweii Ali is a Libyan academic and educator with extensive experience in English language teaching, translation studies, and teacher training. She holds a PhD in Specialised Translation (Translation and Technology) from Medea University, Algeria. Dr Ali has served as a lecturer at the University of Tripoli, where she held leadership positions as Head of the Department of Translation, Head of the Department of Research, Training, and Consultation. Dr Ali worked as a TOT with the National Teacher Training Centre and the Ministry of Education, delivering teacher training programs at national and international levels.

References

Al-Ghamdi, R. (2024). Exploring the impact of ChatGPT-generated feedback on technical writing skills of computing students: A blinded study. Education and Information Technologies, 29, 18901–18926. DOI: https://doi.org/10.1007/s10639-024-12594-2

Alghamdi, L. H., & Alghizzi, T. M. (2025). Educators’ reflections on AI-automated feedback in higher education: A structured integrative review of potentials, pitfalls, and ethical dimensions. Frontiers in Education, 10. DOI: https://doi.org/10.3389/feduc.2025.1704820

Bruton, A. (2007). Vocabulary learning from dictionary referencing and language feedback in EFL translational writing. Language Teaching Research, 11(4), 413–431. DOI: https://doi.org/10.1177/1362168807080961

Carvalho, C., Martins, D., Santana, L. E., & Feliciano, L. (2014). Teacher feedback: Educational guidance in different school contexts. Procedia - Social and Behavioral Sciences, 159, 219–223. DOI: https://doi.org/10.1016/j.sbspro.2014.12.360

Catford, J. C. (1965). A linguistic theory of translation. Oxford University Press.

Cui, Y., Schunn, C. D., & Gai, X. (2022). Peer feedback and teacher feedback: A comparative study of revision effectiveness in writing instruction for EFL learners. Higher Education Research and Development, 41(6), 1838–1854. DOI: https://doi.org/10.1080/07294360.2021.1969541

Garzón, J., Patiño, E., & Marulanda, C. (2025). Systematic review of artificial intelligence in education: Trends, benefits, and challenges. Multimodal Technologies and Interaction, 9(8). DOI: https://doi.org/10.3390/mti9080084

Guasch, T., Espasa, A., Alvarez, I. M., & Kirschner, P. A. (2013). Effects of feedback on collaborative writing in an online learning environment. Distance Education, 34(3), 324–338. DOI: https://doi.org/10.1080/01587919.2013.835772

Hattie, J., & Timperley, H. (2007). The power of feedback. Review of Educational Research, 77(1), 81–112. DOI: https://doi.org/10.3102/003465430298487

Hurtado Albir, A. (2015). The acquisition of translation competence: Competences, tasks, and assessment in translator training. Meta, 60(2), 256–280. DOI: https://doi.org/10.7202/1032857ar

Lee, K.-F., & Yuan, S. (2025). Integration of cultural competence and intercultural communication skills in translation training to promote diversity and inclusivity: A narrative review. In Global perspectives on translation and interpreting (pp. 121–160). IGI Global. DOI: https://doi.org/10.4018/979-8-3693-6463-5.ch005

Li, X., & Ke, P. (2022). An empirical study of peer feedback in translation didactics: Quality, response and student perceptions. Assessment & Evaluation in Higher Education, 47(8), 1231–1244. DOI: https://doi.org/10.1080/02602938.2022.2044013

Lu, Q., Yao, Y., Xiao, L., Yuan, M., Wang, J., & Zhu, X. (2024). Can ChatGPT effectively complement teacher assessment of undergraduate students’ academic writing? Assessment & Evaluation in Higher Education, 49(5), 616–633. DOI: https://doi.org/10.1080/02602938.2024.2301722

Lyu, Y., & Han, Z. (2023). Applying data-driven learning in self-translation of academic discourse: A case study of a Chinese medical student. Frontiers in Psychology, 14, 1071123. DOI: https://doi.org/10.3389/fpsyg.2023.1071123

Man, D., Zhu, C., Chau, M. H., & Maruthai, E. (2022). Contextualizing assessment feedback in translation education: A corpus-assisted ecological approach. Frontiers in Psychology, 13. DOI: https://doi.org/10.3389/fpsyg.2022.1057018

Mindner, L., Schlippe, T., & Schaaff, K. (2023). Classification of human- and AI-generated texts: Investigating features for ChatGPT. In International Conference on Asian language processing (pp. 110–125). Springer. DOI: https://doi.org/10.1007/978-981-99-7947-9_12

Narciss, S. (2008). Feedback strategies for interactive learning tasks. In J. M. Spector, M. D. Merrill, J. van Merriënboer, & M. P. Driscoll (Eds.), Handbook of research on educational communications and technology (3rd ed., pp. 125–144). Lawrence Erlbaum Associates.

Newmark, P. (1988). A textbook of translation. Shanghai Foreign Language Education Press.

Nguyen, T. T. H. (2023). EFL teachers’ perspectives toward the use of ChatGPT in writing classes: A case study at Van Lang University. International Journal of Language Instruction, 2(3), 1–47. DOI: https://doi.org/10.54855/ijli.23231

Schmidt-Fajlik, R. (2023). ChatGPT as a grammar checker for Japanese English language learners: A comparison with Grammarly and ProWritingAid. AsiaCALL Online Journal, 14(1), 105–119. DOI: https://doi.org/10.54855/acoj.231417

Sheen, Y. (2011). Corrective feedback, individual differences and second language learning. Springer. DOI: https://doi.org/10.1007/978-94-007-0548-7

Shi, H., & Aryadoust, V. (2024). A systematic review of AI-based automated written feedback research. ReCALL, 36(2), 187–209. DOI: https://doi.org/10.1017/S0958344023000265

Sun, S.-C. (2015). The importance of professional knowledge in translation. OALib, 02(03), 1–6. DOI: https://doi.org/10.4236/oalib.1101331

Thorp, H. H. (2023). ChatGPT is fun, but not an author. Science, 379(6630), 313. DOI: https://doi.org/10.1126/science.adg7879

Washbourne, K. (2014). Beyond error marking: Written corrective feedback for a dialogic pedagogy in translator training. The Interpreter and Translator Trainer, 8(2), 240–256. DOI: https://doi.org/10.1080/1750399X.2014.908554

Zhang, A., Gao, Y., Suraworachet, W., Nazaretsky, T., & Cukurova, M. (2025). Evaluating trust in AI, human, and co-produced feedback among undergraduate students. British Journal of Educational Technology.

Zhang, K. (2023). LLM: From Transformers to ChatGPT. Robert H. Smith School of Business, University of Maryland

Zheng, Y., Zhong, Q., Yu, S., & Li, X. (2020). Examining students’ responses to teacher translation feedback: Insights from the perspective of student engagement. SAGE Open, 10(2). DOI: https://doi.org/10.1177/2158244020932536