Interview AI-ssistant: Designing for Real-Time Human-AI Collaboration in Interview Preparation and Execution

TL;DR

The paper tackles how to design real-time AI support for qualitative interviewing, bridging preparation and live execution. It introduces Interview AI-ssistant and reports findings from four interconnected studies (formative needs assessment; AI-assisted preparation prototype; controlled experiments on real-time AI during interviews; field deployment) to evaluate effectiveness, usability, and ethical considerations. The results offer design guidelines for synchronous, human-centered AI interfaces that augment interviewer expertise without replacing it, and reveal patterns of collaboration and trust in AI-assisted interviewing. The work contributes to Intelligent User Interfaces by articulating practical, evaluable strategies for AI-enhanced qualitative research and demonstrates potential improvements in interview depth, efficiency, and data quality.

Abstract

Recent advances in large language models (LLMs) offer unprecedented opportunities to enhance human-AI collaboration in qualitative research methods, including interviews. While interviews are highly valued for gathering deep, contextualized insights, interviewers often face significant cognitive challenges, such as real-time information processing, question adaptation, and rapport maintenance. My doctoral research introduces Interview AI-ssistant, a system designed for real-time interviewer-AI collaboration during both the preparation and execution phases. Through four interconnected studies, this research investigates the design of effective human-AI collaboration in interviewing contexts, beginning with a formative study of interviewers' needs, followed by a prototype development study focused on AI-assisted interview preparation, an experimental evaluation of real-time AI assistance during interviews, and a field study deploying the system in a real-world research setting. Beyond informing practical implementations of intelligent interview support systems, this work contributes to the Intelligent User Interfaces (IUI) community by advancing the understanding of human-AI collaborative interfaces in complex social tasks and establishing design guidelines for AI-enhanced qualitative research tools.