Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies

TL;DR

This paper presents a framework using GPT-4 to assist legal experts in thematic analysis, improving coding quality and theme discovery in empirical legal studies through collaborative AI-human interaction.

Contribution

It introduces a novel framework for integrating large language models into the thematic analysis process in legal research, enhancing collaboration and efficiency.

Findings

GPT-4 generated reasonable initial codes

Model improved code quality with expert feedback

Themes discovered by GPT-4 aligned well with legal experts' themes

Abstract

Thematic analysis and other variants of inductive coding are widely used qualitative analytic methods within empirical legal studies (ELS). We propose a novel framework facilitating effective collaboration of a legal expert with a large language model (LLM) for generating initial codes (phase 2 of thematic analysis), searching for themes (phase 3), and classifying the data in terms of the themes (to kick-start phase 4). We employed the framework for an analysis of a dataset (n=785) of facts descriptions from criminal court opinions regarding thefts. The goal of the analysis was to discover classes of typical thefts. Our results show that the LLM, namely OpenAI's GPT-4, generated reasonable initial codes, and it was capable of improving the quality of the codes based on expert feedback. They also suggest that the model performed well in zero-shot classification of facts descriptions in terms of the themes. Finally, the themes autonomously discovered by the LLM appear to map fairly well to the themes arrived at by legal experts. These findings can be leveraged by legal researchers to guide their decisions in integrating LLMs into their thematic analyses, as well as other inductive coding projects.