近年生成式人工智慧快速發展，其於質性研究資料分析中的應用潛力逐漸受到關注，此一趨勢在分析歷程具高複雜性且費時的主題分析方法中尤為明顯。為回應教育研究中質性分析效率與方法嚴謹性之雙重需求，本研究以教育研究情境為例，探討ChatGPT作為分析輔助工具應用於主題分析之可行性與實務操作方式。研究依循Braun與Clarke所提出之主題分析六步驟，透過具結構性的提示詞設計，引導ChatGPT協助進行資料理解、初步編碼、主題建構、概念統整與研究報告撰寫，並以大學生於全英文授課（English as a Medium of Instruction, EMI）課程中的學習經驗作為實測案例。實測結果顯示，ChatGPT在編碼與主題發展階段能有效擴展分析視角，提升資料整理與主題辨識效率，並有助於揭示傳統人工分析中可能被忽略的意涵。最後，本研究指出ChatGPT適合被定位為質性研究的分析輔助角色，而非取代研究者的主導角色，研究結果可作為教育研究導入生成式人工智慧輔助主題分析之方法參考。

In recent years, the rapid development of generative artificial intelligence has drawn increasing scholarly attention to its potential applications in qualitative data analysis, particularly in thematic analysis, which is characterized by complex and time-intensive analytical procedures. In response to the dual demands of analytical efficiency and methodological rigor in educational research, this study examines the feasibility and practical implementation of ChatGPT as an analytical support tool for thematic analysis within an educational research context. Guided by the six-phase framework of thematic analysis proposed by Braun and Clarke, the study employs systematically designed prompts to support ChatGPT in assisting with data familiarization, initial coding, theme development, conceptual integration, and academic report writing. Interview data on university students’ learning experiences in English as a Medium of Instruction (EMI) courses were used as a case. The findings indicate that ChatGPT is effective in broadening analytical perspectives during the coding and theme development stages, enhancing the efficiency of data organization and theme identification, and revealing nuances that may be overlooked in traditional analysis. Overall, this study suggests that ChatGPT is best positioned as an analytical assistant in qualitative research rather than a substitute for the researcher’s interpretive authority. The findings offer methodological insights for the integration of generative artificial intelligence into thematic analysis in educational research.