TALLMesh: a simple application for performing Thematic Analysis with Large Language Models
This tool addresses the problem of limited coding skills in fields like social sciences and humanities, offering a practical solution for qualitative research, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the challenge of making thematic analysis accessible to non-technical researchers by developing TALLMesh, a GUI application that uses LLMs to assist in generating and refining codes and themes from textual data, enabling iterative human-in-the-loop processes without coding.
Thematic analysis (TA) is a widely used qualitative research method for identifying and interpreting patterns within textual data, such as qualitative interviews. Recent research has shown that it is possible to satisfactorily perform TA using Large Language Models (LLMs). This paper presents a novel application using LLMs to assist researchers in conducting TA. The application enables users to upload textual data, generate initial codes and themes. All of this is possible through a simple Graphical User Interface, (GUI) based on the streamlit framework, working with python scripts for the analysis, and using Application Program Interfaces of LLMs. Having a GUI is particularly important for researchers in fields where coding skills may not be prevalent, such as social sciences or humanities. With the app, users can iteratively refine codes and themes adopting a human-in-the-loop process, without the need to work with programming and scripting. The paper describes the application key features, highlighting its potential for qualitative research while preserving methodological rigor. The paper discusses the design and interface of the app and outlines future directions for this work.