Exploring second language writers’ engagement with ChatGPT feedback: Revision behaviors and perceptions

While recent research underlines ChatGPT's potential as a second language (L2) writing feedback tool, its effectiveness and role in engaging L2 writers require further investigation. This study explores how English as a Foreign Language (EFL) writers engage with ChatGPT feedback by analyzing their revision behaviors and perceptions of its effectiveness in revising their opinion essays. Using a convergent parallel mixed methods design, the study involved 25 B1-level EFL students from a university in Türkiye. Data were collected through essay drafts, change tracker sheets, a questionnaire, and interviews. The descriptive and thematic analysis of essays, change tracker sheets, and interviews revealed that most content and language feedback was accepted, while organization feedback received mixed engagement of acceptance and rejection. Students were more likely to accept language use feedback than content or organization feedback, often incorporating ChatGPT's revisions directly. For content feedback, the most common revision operations were additions and substitutions while more than a third of the revisions in response to organization feedback involved no corrections. Correction was the most frequent revision operation for language use feedback. Questionnaire and interview analyses further revealed that while ChatGPT feedback was generally well-received and considered beneficial for writing improvement, students faced challenges related to feedback length, specificity, advanced language, and misunderstandings. This study provides valuable insights into how EFL students interact with ChatGPT-generated feedback, highlighting both its potential to support L2 writing development and the challenges that may limit its effectiveness.