VietTESOL International Convention 2026

This study compares advanced English-major students’ applications of feedback generated by ChatGPT and Microsoft Copilot in improving language use in college writing essays. It aims to compare the differences across four aspects of language use, lexical accuracy, grammatical accuracy, vocabulary range, and sentence complexity after using ChatGPT and Microsoft Copilot feedback in the students’ writing, as well as to explore their engagement with both tools generated feedback during the revision process. A sequential mixed-methods design is adopted. Data are collected from 31 English-major students through a writing task and from 10 representatives through semi-structured interviews. Quantitative data were analyzed using one-way repeated measures ANOVA, while qualitative data were analyzed using thematic analysis to identify patterns in students’ engagement with AI-generated feedback. The findings indicate significant differences in three out of four language aspects after revision using ChatGPT and Microsoft Copilot feedback, except for sentence complexity. Microsoft Copilot post-feedback version shows a stronger difference in terms of lexical accuracy. Regarding students’ engagement, students generally perceive both tools as clear and useful for revision. ChatGPT is valued for providing broader and more varied suggestions but is sometimes cognitively demanding. In contrast, Microsoft Copilot is seen as more concise, focus, and easier to apply. Students also demonstrate active, selective, and context-dependent engagement with both AI tools. The study suggests pedagogical implications at the local level for students and teachers, and at a broader level for institutions, curriculum designers, and educational technology developers.