AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers

Prof. Dr. Karsten Donnay together with the DSI Community Democracy are pleased to welcome Christopher Klamm (University of Mannheim) for a lecture on topic «AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers».

The talk is based on a recent working paper written in collaboration with Alexander Wuttke, Matthias Assenmacher, Max Lang, Quirin Würschinger and Frauke Kreuter.

Please find an abstract of the paper below:

Traditional methods for eliciting people’s opinions face a trade-off between depth and scale: structured surveys enable large-scale data collection but limit respondents’ ability to express unanticipated thoughts in their own words, while conversational interviews provide deeper insights but are resource-intensive. This study explores the potential of replacing human interviewers with large language models (LLMs) to conduct scalable conversational interviews. Our goal is to assess the performance of AI Conversational Interviewing and to identify opportunities for improvement in a controlled environment. We conducted a small-scale, in-depth study with university students who were randomly assigned to be interviewed by either AI or human interviewers, both employing identical questionnaires on political topics. Various quantitative and qualitative measures assessed interviewer adherence to guidelines, response quality, participant engagement, and overall interview efficacy. The findings indicate the viability of AI Conversational Interviewing in producing quality data comparable to traditional methods, with the added benefit of scalability. Based on our experiences, we present specific recommendations for effective implementation.

When / Wann: October 22, 2024, 10:00 - 11:30

Where / Wo: University of Zurich, Room AFL-E-003, Affolternstrasse 56, 8050 Zurich

Language / Sprache:  English

Organisation: DSI Community Democracy

Back to event overview