MimiTalk: Revolutionizing Qualitative Research with Dual-Agent AI
This work addresses the problem of replicable and quality-controlled qualitative research for social scientists, though it appears incremental as it builds on existing AI methods for data collection.
The paper tackles the challenge of scalable and ethical conversational data collection in social science research by introducing MimiTalk, a dual-agent constitutional AI framework, and finds that it reduces interview anxiety and outperforms human interviews in metrics like information richness and coherence.
We present MimiTalk, a dual-agent constitutional AI framework designed for scalable and ethical conversational data collection in social science research. The framework integrates a supervisor model for strategic oversight and a conversational model for question generation. We conducted three studies: Study 1 evaluated usability with 20 participants; Study 2 compared 121 AI interviews to 1,271 human interviews from the MediaSum dataset using NLP metrics and propensity score matching; Study 3 involved 10 interdisciplinary researchers conducting both human and AI interviews, followed by blind thematic analysis. Results across studies indicate that MimiTalk reduces interview anxiety, maintains conversational coherence, and outperforms human interviews in information richness, coherence, and stability. AI interviews elicit technical insights and candid views on sensitive topics, while human interviews better capture cultural and emotional nuances. These findings suggest that dual-agent constitutional AI supports effective human-AI collaboration, enabling replicable, scalable and quality-controlled qualitative research.