ISCA: A Framework for Interview-Style Conversational Agents

TL;DR

ISCA is a low-compute, non-generative framework for interview-style conversational agents that facilitates qualitative data collection and analysis, with easy customization and open-source code for diverse applications.

Contribution

The paper introduces a novel, accessible framework for interview-style conversational agents that does not rely on generative models, enabling controlled interactions and easy customization.

Findings

Successfully applied to COVID-19 expressive interviewing

Effective in surveying public opinion on neurotechnology

Open-source implementation for community use

Abstract

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.