A Comparative Study of Google Gemini and ChatGPT in Enhancing English Language Learning for EFL Learners: A Case Study of the English Research Writing Course

Abstract

This study compared Google Gemini and ChatGPT's effectiveness for enhancing the academic writing skills of English as a Foreign Language (EFL) learners in eight-week research writing course in two Thai universities. Using a quasi-experimental approach, 80 third-year learners of a private university (HCU) and a public university (NRRU) were assigned to use either ChatGPT or Google Gemini for writing tasks. Pre- and post-intervention writing assessments, Technology Acceptance Model-inspired Likert-scale questionnaires, and semi-structured interviews were employed to measure writing ability gains, learner attitudes, and learning engagement. The results indicate that both tools effectively improved linguistic accuracy and essay structure, and Gemini was found to work better than ChatGPT in multimodal feedback and source integration, particularly among rural learners (p < .05, Cohen's d = 0.62). However, overdependence and plagiarism risk were cited as issues. Qualitative findings suggest increased learner confidence and motivation, but also require adjustment of implementation in rural areas because of cultural and technological constraints. This underscores AI's promise in EFL writing instruction, emphasizing instructor guidance and AI literacy in Thai contexts. Pedagogical implications include hybrid AI models for low-resource settings, with calls for further longitudinal research.