Enhancing IELTS writing task 2 performance through AI-generated feedback: A mixed-methods study on learner improvement and perceptions

Abstract

This study investigates the impact of AI-generated feedback on English as a Foreign Language (EFL) learners' performance in IELTS Writing Task 2 and their perceptions of the feedback process. Employing a convergent mixed-method design, the research involved 18 undergraduate students who completed four iterative writing tasks using official IELTS prompts.  After each submission, participants received immediate feedback from a custom-developed AI tool powered by GPT-4, aligned with IELTS writing and descriptors. Quantitative data were collected through pre- and post-feedback essay scores across four assessment criteria: Task Response, Coherence and cohesion, lexical resource, and Grammatical Range and Accuracy, rated by certified IELTS examiners. Qualitative data were gathered through open-ended questionnaire responses. Findings revealed significant improvements in all four writing criteria over a four-week intervention period, particularly in grammatical range and lexical resource. Learners reported high levels of satisfaction with the AI-feedback, citing clarity, immediacy, and non-judgmental tone as motivating factors. Thematic analysis also indicated increased learner autonomy and deeper engagement with revision practices. These results suggest that AI-generated feedback can serve as an effective pedagogical tool in high-stakes test preparation contexts. Implications for writing instruction, learner training, and the integration of AI in EFL classroom are discussed.