Search for: All records

This study explores the application of artificial intelligence (AI) in qualitative research, specifically examining how large language models (LLMs) can be utilized to code qualitative data and identify relationships among coder-defined themes. The approach is particularly useful for cases where researchers have previously-identified themes and hypotheses but lack the resources to code a large corpus of data manually. We outline a multi-step methodological framework grounded in qualitative research traditions, whereby researchers first conduct manual coding using a grounded theory approach (Charmaz, 2006; Glaser & Strauss, 1967) on a subset of the data. The resulting codes are then applied to the remaining data using a model-assisted process that integrates natural language processing, AI-based text classification (Noah et al., 2024), and topic identification. Lastly, this is followed by statistical analyses to test hypotheses and expected patterns, providing a robust approach to ensure reliability and accuracy. We illustrate this process through the systematic application of locally-run AI for coding interview transcripts related to graduate students’ experiences in four Ph.D. programs at a large research university. We demonstrate how AI can improve the efficiency, consistency, and scalability of qualitative research without sacrificing confidentiality. This study highlights the potential for AI to enhance qualitative research processes while addressing challenges related to nuance and interpretation.