AI of Oz: Enhancing Wizard of Oz Studies in HCI with AI Assistance for Human Moderation

要旨

The Wizard of Oz (WoZ) method is a common and popular approach for simulating interactive systems in Human-Computer Interaction. Running such studies is demanding for researchers because the human wizard must manage human–agent interactions in real time while keeping participants safe and the interaction natural. Many WoZ systems struggle to reproduce complex agent behaviours without minimal delays or heavy workload for the moderator. We introduce AI of Oz, a framework that uses large language models to support researchers by monitoring ongoing interactions, detecting sensitive moments, and suggesting contextually appropriate responses. In a study with 20 HCI-related researchers, the system improved participants’ ability to manage interactions and maintain control compared to a version without AI support. We outline implications for WoZ research and note current limitations and future directions.

著者
Ruoyu Wen
University of Canterbury, Christchurch, New Zealand
Kunal Gupta
The University of Auckland, Grafton, Auckland, New Zealand
Kekayan Nanthakumar
The University Of Auckland, Auckland, New Zealand
Binyang Han
University of Canterbury, Christchurch, New Zealand
Simon Hoermann
University of Canterbury, Christchurch, Canterbury, New Zealand
Mark Billinghurst
University of South Australia, Mawson Lakes, Australia
Alaeddin Nassani
University of Auckland, Auckland, New Zealand
D D. Allan
University of Canterbury, Christchurch, New Zealand
Thammathip Piumsomboon
University of Canterbury, Christchurch, Canterbury, New Zealand

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: Research Methodology & UX

P1 - Room 134
7 件の発表
2026-04-16 20:15:00
2026-04-16 21:45:00