Exploring the synergy of human and AI-driven approaches in thematic analysis for qualitative educational research

Author:
Open Access
Publisher website
Google Scholar
Abstract
This paper investigates the integration of Generative Artificial Intelligence (GenAI), particularly Large Language Models (LLMs) such as GPT-4, into qualitative analysis in educational research. Utilizing TRACER (Transcript Analysis and Concept Extraction Resource), a GenAI-driven tool, the study evaluated its efficiency, reproducibility, and synergy with human analytical expertise. The research demonstrated that TRACER significantly streamlined thematic analysis, efficiently handled large data volumes, and maintained consistency in theme identification. The findings reveal that integrating TRACER’s computational power with human interpretive skills enriches research outcomes, suggesting a collaborative approach for optimal results. Despite its efficacy, limitations such as data scope and current GenAI capabilities are acknowledged, indicating areas for future development. This paper contributes to the understanding of GenAI’s role in qualitative research, proposing it as a valuable tool for overcoming traditional challenges in the field and highlighting the importance of human-AI collaboration for comprehensive and nuanced analyses in educational research.

This publication has 17 references indexed in Scilit: