MimiTalk: Revolutionizing Qualitative Research with Dual-Agent AI

TL;DR

MimiTalk introduces a dual-agent AI framework that enhances qualitative research by providing scalable, ethical, and high-quality conversational data collection, outperforming human interviews in key metrics and supporting effective human-AI collaboration.

Contribution

The paper presents MimiTalk, a novel dual-agent constitutional AI system for scalable, ethical qualitative data collection, demonstrating its effectiveness through multiple studies.

Findings

Reduces interview anxiety and maintains coherence.

Outperforms human interviews in information richness and stability.

Elicits technical insights and candid views on sensitive topics.

Abstract

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.