AI Feedback vs. Teacher Feedback: A Comparative Study of English-Speaking Practice among L1 Mandarin EFL Learners

Abstract

Speaking is a major challenge for many L1 Mandarin learners preparing for IELTS. This study compared AI-supported and teacher-led feedback in an eight-session online IELTS Speaking programme. Using a mixed methods design, the study involved 24 participants, with 13 receiving AI-supported feedback through Doubao-Seed-2.0, a generative AI chatbot, and 11 receiving teacher-led feedback. Outcomes were examined through official IELTS Speaking scores and learner survey responses. While both groups showed significant within-group gains in IELTS Speaking, the between-group comparison did not detect a significant difference in speaking gain. Participants in both groups reported greater confidence and clearer expression. AI-supported participants particularly valued answer expansion, alternative expressions, and repeated practice, while teacher-led participants valued pronunciation correction, live explanation, and classroom interaction. The findings suggest that the two feedback modes may offer different but complementary forms of support. A reflection chapter further examines the researcher’s experiences of using AI in both teaching and research, highlighting the importance of teacher judgement, careful prompt design, and critical AI use.