Using Large Language Model to Support Flexible and Structural Inductive Qualitative Analysis

2025-01-01

AI Summary

Qualitative analysis in informal settings—such as meeting summaries or personal ideation—lacks rapid, structured computational support. Method: This paper introduces MindCoder, the first lightweight, LLM-driven inductive analysis tool integrating a “code-to-theory” paradigm. Built on GPT-4o, it unifies prompt engineering, iterative human-AI collaboration, and an automated coding pipeline to perform end-to-end open coding, axial coding, and concept generation—balancing analytical efficiency with theoretical rigor. Contribution/Results: A user study (N=12) demonstrates that MindCoder significantly improves analytical flexibility and structural coherence over ChatGPT and Atlas.ti Web AI, reduces task completion time by ~60%, and accelerates consensus formation. Its core innovation lies in embedding grounded theory logic directly into the LLM workflow, enabling interpretable, traceable, and fully automated theory generation without requiring manual coding manuals.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Analogy
• Humans and AI: Understanding People, Theories, Concepts and Methods

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Traditional qualitative analysis requires significant effort and collaboration to achieve consensus through formal coding processes, including open coding, discussions, and codebook merging. However, in scenarios where such rigorous and time-intensive methods are unnecessary-such as summarizing meetings or personal ideation-quick yet structual insights are more practical. To address this need, we proposed MindCoder, a tool inspired by the"Codes-to-theory"model and developed through an iterative design process to support flexible and structural inductive qualitative analysis. With OpenAI's GPT-4o model, MindCoder supports data preprocessing, automatic open coding, automatic axial coding, and automatic concept development, ultimately presenting a report to support insights presentation. An evaluation with 12 participants highlights its effectiveness in enabling flexible yet structured analysis and its advantages over ChatGPT and Atlas.ti Web AI coding function.

Problem

• Rapid Insight Analysis
• Non-Formal Coding Process
• Structured Analysis

Innovation

• MindCoder
• GPT-4
• Qualitative Analysis Automation