From Assistance to Autonomy -- A Researcher Study on the Potential of AI Support for Qualitative Data Analysis

2025-01-31

AI Summary

This study addresses core challenges in applying AI—particularly large language models—to qualitative data analysis (QDA): privacy risks, diminished researcher agency, and insufficient output credibility. Drawing on in-depth interviews with 15 HCI researchers, we propose the first QDA-AI co-creation spectrum framework that jointly prioritizes researcher autonomy, data privacy, and analytical trustworthiness. The framework systematically characterizes a progressive continuum of AI involvement—from minimal to maximal—across authentic QDA workflows, including data preprocessing, researcher onboarding, and intermediate analysis. Through human-centered AI design modeling and workflow mapping, we derive an actionable AI-intervention scenario matrix and four archetypal application patterns. Practitioner validation confirms that the framework enhances analytical efficiency while preserving epistemic agency and ethical compliance. It thus provides both a theoretical foundation and practical guidance for developing responsible, human-centered QDA-AI collaboration paradigms.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The advent of AI tools, such as Large Language Models, has introduced new possibilities for Qualitative Data Analysis (QDA), offering both opportunities and challenges. To help navigate the responsible integration of AI into QDA, we conducted semi-structured interviews with 15 HCI researchers experienced in QDA. While our participants were open to AI support in their QDA workflows, they expressed concerns about data privacy, autonomy, and the quality of AI outputs. In response, we developed a framework that spans from minimal to high AI involvement, providing tangible scenarios for integrating AI into HCI researchers' QDA practices while addressing their needs and concerns. Aligned with real-life QDA workflows, we identify potentials for AI tools in areas such as data pre-processing, researcher onboarding, or mediation. Our framework aims to provoke further discussion on the development of AI-supported QDA and to help establish community standards for their responsible use.

Problem

• Artificial Intelligence
• Qualitative Data Analysis
• Privacy and Security

Innovation

• Artificial Intelligence in Qualitative Data Analysis
• Gradual AI Integration
• Data Security and Accuracy