Formative feedback across sources: Student perceptions and writing outcomes with instructor, peer, and AI-generated feedback

Abstract Previous research has highlighted the critical role of instructor and peer feedback in developing students’ writing. Although artificial intelligence (AI)-generated feedback, such as that from ChatGPT, may not yet match the depth of human evaluators, it offers a valuable resource for early drafts. In this exploratory study, 29 students from an upper-division English writing class at a public university in the western U.S. participated, sharing their perceptions of feedback from the writing instructor, an assigned peer, and generative AI when revising their research papers. Using quantitative and qualitative analyses of writing and survey data, we found that students significantly improved their writing quality across drafts after receiving feedback from these three sources. Survey responses revealed that instructor feedback was highly valued for its relevance and constructive suggestions, while both peer and AI-generated feedback were appreciated for their clarity, alignment with the writing content, and personal connection. Students recognized that each feedback source brought unique strengths to their academic writing process, indicating the importance of a multi-layered approach to feedback practices. These findings suggest that a multi-layered feedback approach may play a valuable role in supporting students’ academic writing development, with broader implications for teaching English writing at universities across North America and beyond.