Bridging Interpretation and Automation: A Bibliometric Review of AI-Assisted Qualitative Research (Extended Abstract)

Abstract

The rapid advancement of Large Language Models (LLMs) is transforming qualitative inquiry by augmenting labor-intensive interpretive workflows. This study conducts a bibliometric analysis to examine the knowledge structure and methodological evolution of AI-assisted qualitative research. Using an LLM-assisted screening framework, we identified and analyzed 431 relevant publications from the Scopus and Web of Science databases. The findings reveal an exponential growth in publications since 2022, reflecting a methodological transition from traditional rule-based text mining toward AI-assisted and interactive qualitative analysis. Keyword network analysis shows that although ChatGPT is the most frequently utilized tool, Natural Language Processing (NLP) occupies the most structurally central position within the knowledge network, while prompt engineering functions as a key intermediary linking computational techniques with qualitative analytical practices. Methodologically, AI applications are primarily concentrated in coding- and procedure-oriented approaches, particularly thematic analysis and qualitative coding. In contrast, the integration of AI into highly interpretive traditions such as grounded theory and discourse analysis remains comparatively limited due to persistent concerns regarding contextual interpretation, sociocultural nuance, researcher reflexivity, and algorithmic bias. Overall, the findings suggest that AI is increasingly conceptualized as a collaborative co-analyst rather than an autonomous interpreter within qualitative inquiry, highlighting the growing importance of robust human-AI collaboration frameworks to ensure methodological rigor and ethical accountability.