Comparing peer, ChatGPT, and teacher corrective feedback in EFL writing: Students' perceptions and preferences

Abstract

The effectiveness of Written Corrective Feedback (WCF) provision in English as a Foreign Language (EFL) classrooms for enhancing students’ writing has been well-established. With the advent of various feedback modes in modern classrooms, this pilot study aims to explore EFL students’ perceptions and preferences regarding the effectiveness of three distinct feedback modes: peer feedback, artificial intelligence (AI), and teacher feedback. The study also aimed to determine the distribution of feedback across specific components of writing, while accounting for revisions made. Fifteen pairs of participants were assigned to complete a brief writing task, followed by receiving WCF from peers, an AI tool (ChatGPT), and the teacher. Subsequent revisions to their writing were made after each feedback mode. A qualitative approach utilizing a survey was used for data collection and analysis. Results indicated that participants perceived both ChatGPT and teacher feedback as effective, with peer feedback also being generally regarded as effective by most participants. Preferences leaned towards receiving teacher WCF, as well as a combination of teacher and ChatGPT WCF. Furthermore, the study identified the proportion of feedback allocated to specific writing components, with subsequent discussions regarding implications. These findings have potential implications for refining feedback practices within EFL classrooms.

Keywords

• written corrective feedback (WCF)
• English as a Foreign Language (EFL)
• peer feedback
• artificial intelligence (AI) feedback