Peer feedback and ChatGPT-generated feedback on Japanese EFL students’ engagement in a foreign language writing context

Abstract

In Second Language Acquisition (SLA), affective, behavioral, and cognitive engagements play crucial roles in how learners interact with and process written feedback on their language production. The present study investigates the efficacy of peer feedback versus ChatGPT-generated feedback in an English as a Foreign Language (EFL) writing context. Participants (n = 324) were 1^st and 2^nd-year undergraduate students at a Japanese university. The peer group (n = 164) received peer feedback, while the ChatGPT group (n = 160) utilized ChatGPT with crafted prompts for feedback. A survey instrument measuring three engagements, i.e., affective, behavioral, and cognitive engagement, was conducted at the end of the semester. Results revealed that all three types of engagements were higher in the ChatGPT group than those in peer feedback group. However, significant differences were suggested in only affective and behavioral engagements, with the difference in cognitive engagement remaining non-significant. The findings suggest that while ChatGPT-generated feedback can be integrated into EFL instruction, its impact on student engagement, particularly affective and behavioral, warrants careful consideration. Pedagogical implications are discussed.