用双智能体AI提升社科访谈效率与质量，减少焦虑且信息更丰富。
MimiTalk: Revolutionizing Qualitative Research with Dual-Agent AI
- 双代理架构：监督模型统筹策略，对话模型生成问题。
- AI访谈在信息量、连贯性上超越人类访谈，尤其适合敏感话题。
- 适合需要大规模、可复现、高质量访谈的社科研究者。
我们提出MimiTalk，一种用于社会科学研究中可扩展且合乎伦理的对话数据收集的双代理宪法式AI框架。该框架整合了监督模型进行战略管控，以及对话模型生成提问。我们进行了三项研究：研究1通过20名参与者评估可用性；研究2利用NLP指标和倾向性得分匹配，对比了121场AI访谈与1,271场来自MediaSum数据集的人类访谈；研究3则由10位跨学科研究者分别开展人机访谈，并进行盲法主题分析。结果显示，MimiTalk能降低访谈焦虑，保持对话连贯性，且在信息丰富度、连贯性和稳定性上优于人类访谈。AI访谈更易获取技术见解和对敏感话题的坦诚反馈，而人类访谈则更擅长捕捉文化与情感细节。这些发现表明，双代理宪法式AI支持有效的人机协作，推动可重复、可扩展、质量可控的定性研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。