Improving Experimental Methods to Capture Real-World Human-AI Perceptions and Interactions

Authors: N Haduong

Published: 2025

Publication: 2025 - search.proquest.com

The research focuses on developing methodologies to bridge the gap between controlled laboratory studies and real-world human-AI perceptions and interactions, promoting task immersion and intrinsic motivation to model realistic behaviors.

Methods: Used task immersion techniques, domain-specific recruitment, error taxonomy development, and CPS-TaskForge environment generator for systematic study of collaborative problem solving and AI-assisted decision-making.

Key Findings: Human perceptions of AI in collaborative problem solving, understanding risks in AI-assisted decision making, and user behavior under performance pressure with AI advice.

Limitations: Lack of real-world datasets for larger-than-dyad CPS studies and challenges in modeling non-deterministic AI behaviors.

Institution: University of Washington

Research Area: Human-AI Interaction and Perception

Discipline: Human-Computer Interaction (HCI)