ISCA: A Framework for Interview-Style Conversational Agents
This provides a practical tool for researchers and practitioners needing controlled conversational interactions for data collection, though it is incremental as it builds on existing non-generative agent approaches.
The authors tackled the problem of creating interview-style conversational agents for qualitative data collection by developing ISCA, a low-compute non-generative framework that allows easy adjustment through an online administrative panel without coding. They demonstrated its utility in two case studies, including COVID-19 expressive interviewing and neurotechnology opinion surveys, with the code being open-source for further development.
We present a low-compute non-generative system for implementing interview-style conversational agents which can be used to facilitate qualitative data collection through controlled interactions and quantitative analysis. Use cases include applications to tracking attitude formation or behavior change, where control or standardization over the conversational flow is desired. We show how our system can be easily adjusted through an online administrative panel to create new interviews, making the tool accessible without coding. Two case studies are presented as example applications, one regarding the Expressive Interviewing system for COVID-19 and the other a semi-structured interview to survey public opinion on emerging neurotechnology. Our code is open-source, allowing others to build off of our work and develop extensions for additional functionality.