ISCA: A Framework for Interview-Style Conversational Agents

2025-08-19

AI Summary

Qualitative research interviews face challenges including high computational overhead, lack of process controllability, and steep configuration barriers for interview agents. Method: This paper proposes a lightweight, non-generative dialogue agent framework based on a rule-driven architecture that decouples front-end interaction from back-end logic control. It enables zero-code deployment of standardized interview protocols via an online management dashboard and supports structured data collection alongside quantitative analysis capabilities. Contribution/Results: The framework ensures dialogue controllability and reproducibility—critical for attitude tracking and behavioral change monitoring—and adopts an open-source design to facilitate cross-domain extension and iterative functionality enhancement. Empirical validation in two studies—expressive interviews on pandemic experiences and public surveys on neurotechnology attitudes—demonstrates significant reductions in deployment costs and marked improvements in data structuring, confirming the framework’s efficacy and generalizability.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Humans and AI: Intelligent User Interfaces
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Responsible Web: Consent frameworks and practices on the web
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• Developing low-compute non-generative interview conversational agents
• Facilitating qualitative data collection through controlled interactions
• Creating accessible interview tools without coding requirements

Innovation

• Non-generative low-compute system
• Online administrative panel adjustment
• Open-source framework implementation