Generative AI in Qualitative Data Analysis: introducing the Guided AI Thematic Analysis framework скачать в хорошем качестве

Generative AI in Qualitative Data Analysis: introducing the Guided AI Thematic Analysis framework

Generative AI in Qualitative Data Analysis: introducing the Guided AI Thematic Analysis (GAITA) framework Despite emerging scholarship on applying generative AI (GenAI) in qualitative data analysis, this new area remains underdeveloped. This presentation proposes a Guided AI Thematic Analysis (GAITA), an adapted version of King et al.’s (2018) Template Analysis to help qualitative researchers apply Generative AI in thematic analysis process. Based on the PERFECT procedure, this framework positions researchers as a reflexive instrument and intellectual leader while thoroughly guiding GPT-4 in four stages: data familiarization; preliminary coding; template formation and finalization; and theme development. Additionally, I propose the ACTOR framework, a simple approach to combining different effective prompting techniques when working with GenAI for qualitative research purposes. Kien Nguyen-Trung, PhD, is an applied qualitative researcher and disaster sociologist focusing on environmental and social resilience. Currently, he serves as a Research Fellow at Water Sensitive Cities Australia, Monash Sustainable Development Institute, Monash University. He is an editor at The Qualitative Report and serves on editorial boards at Sociological Research Online and International Journal of Qualitative Methods. As founder of both Vietnam Social Research Methodology Forum and Qualitative Methods Centre, he supports the development and innovation of qualitative research communities. His interests span qualitative methods, generative AI, disaster, and vulnerability. Slides available in Zenodo: https://zenodo.org/records/17872630