Comparing teacher E-feedback, AI feedback, and hybrid feedback in enhancing EFL writing skills

Abstract

Effective feedback plays a critical role in enhancing the writing skills of English as a Foreign Language (EFL) learners. This study examines the comparative effectiveness of three feedback approaches—Teacher e-feedback, AI-based feedback, and a hybrid model—in enhancing the writing performance of Iranian intermediate-level EFL learners. A randomized controlled trial was conducted with 88 intermediate-level EFL learners, who were randomly assigned to one of three feedback groups: (1) teacher e-feedback, (2) AI-generated feedback using tools such as ChatGPT and Grammarly, and (3) a hybrid approach that combined both feedback types. Writing proficiency was assessed using IELTS writing tasks and the Oxford Placement Test before and after the intervention. Significant differences were observed between the groups, with the hybrid feedback group showing the most substantial improvements, particularly in task achievement, coherence, and grammatical accuracy. AI feedback was most effective in enhancing lexical resources. Qualitative reflections supported the quantitative findings, with participants in the hybrid group reporting increased confidence, reduced anxiety, and appreciation for the balanced, dual-source feedback. These results highlight the pedagogical potential of integrating human and AI feedback to enhance EFL writing instruction.