Synergizing AI and Human Feedback: Effects of ChatGPT-generated and Teacher Corrective Feedback on Thai EFL Students’ Cause-and-Effect Writing


  •  Raweewat Sripradith    

Abstract

Teacher corrective feedback (TCF) has traditionally aided EFL writing, yet delayed responses and generic guidance often hinder its effectiveness. AI-assisted tools like ChatGPT provide immediate, personalized, and interactive feedback, offering a valuable complement to teacher support and potentially enhancing writing development. This study examined the impact of integrating ChatGPT-generated feedback with TCF on students’ writing abilities in cause-and-effect essays and explored their experiences with this blended approach. An explanatory sequential mixed-methods design was employed, consisting of a quantitative quasi-experimental phase followed by qualitative exploration. Twenty-eight third-year English education students from a Thai university were purposively chosen to participate in ten instructional sessions that combined ChatGPT feedback with TCF for cause-and-effect writing. Pre-tests and post-tests were used to assess students’ writing skills, and their perspectives were further investigated through semi-structured interviews. Results showed significant improvement in students’ writing performance, with statistical analysis confirming a notable difference between pre-and post-test scores p = 0.001 (< 0.05). Qualitative findings supported these results, with students highlighting clearer writing structure, stronger idea generation, improved grammar awareness, complementary feedback, and greater motivation for self-editing. However, challenges such as feedback fatigue and potential over-reliance on AI were also noted. The findings suggest that the synergy of AI and teacher feedback may enhance students’ writing performance; however, challenges remain in employing ChatGPT as an AI-based learning tool.



This work is licensed under a Creative Commons Attribution 4.0 License.