Large Language Model for Qualitative Research -- A Systematic Mapping Study
Cauã Ferreira Barros, Bruna Borges Azevedo, Valdemar Vicente Graciano Neto, Mohamad Kassab, Marcos Kalinowski, Hugo Alexandre D. do Nascimento, Michelle C. G. S. P. Bandeira
TL;DR
This systematic mapping study investigates how large language models are applied to qualitative research, identifying contexts, configurations, methodologies, and evaluation approaches. It finds that LLMs can automate tasks such as open coding and theme extraction with results comparable to traditional methods in several cases, while prompting dependencies and biases present notable challenges. The study emphasizes human–AI collaboration, robust prompt engineering, and the development of standardized evaluation to advance reliable integration of LLMs in qualitative analysis. Overall, the work maps a nascent but rapidly growing field and outlines concrete directions for methodological, architectural, and evaluative improvements to enhance impact in domains including healthcare, education, and cultural studies.
Abstract
The exponential growth of text-based data in domains such as healthcare, education, and social sciences has outpaced the capacity of traditional qualitative analysis methods, which are time-intensive and prone to subjectivity. Large Language Models (LLMs), powered by advanced generative AI, have emerged as transformative tools capable of automating and enhancing qualitative analysis. This study systematically maps the literature on the use of LLMs for qualitative research, exploring their application contexts, configurations, methodologies, and evaluation metrics. Findings reveal that LLMs are utilized across diverse fields, demonstrating the potential to automate processes traditionally requiring extensive human input. However, challenges such as reliance on prompt engineering, occasional inaccuracies, and contextual limitations remain significant barriers. This research highlights opportunities for integrating LLMs with human expertise, improving model robustness, and refining evaluation methodologies. By synthesizing trends and identifying research gaps, this study aims to guide future innovations in the application of LLMs for qualitative analysis.