Qualitative Coding Analysis through Open-Source Large Language Models: A User Study and Design Recommendations

TL;DR

This paper presents ChatQDA, an on-device open-source LLM framework for privacy-preserving qualitative coding, revealing user trust dynamics and offering design insights for secure, rigorous analysis tools.

Contribution

Introduces ChatQDA, a novel local LLM-based framework for qualitative analysis, and provides user-centered design recommendations for privacy and trust.

Findings

Participants rated usability and efficiency highly.

Users showed 'conditional trust' based on surface-level outputs.

Concerns about epistemic uncertainty persisted despite local deployment.

Abstract

Qualitative data analysis is labor-intensive, yet the privacy risks associated with commercial Large Language Models (LLMs) often preclude their use in sensitive research. To address this, we introduce ChatQDA, an on-device framework powered by open-source LLMs designed for privacy-preserving open coding. Our mixed-methods user study reveals that while participants rated the system highly for usability and perceived efficiency, they exhibited "conditional trust", valuing the tool for surface-level extraction while questioning its interpretive nuance and consistency. Furthermore, despite the technical security of local deployment, participants reported epistemic uncertainty regarding data protection, suggesting that invisible security measures are insufficient to foster trust. We conclude with design recommendations for local-first analysis tools that prioritize verifiable privacy and methodological rigor.