Trust plays a fundamental role in shaping the willingness of users to engage and collaborate with artificial intelligence (AI) systems. Yet, measuring user trust remains challenging due to its complex and dynamic nature. While traditional survey methods provide trust levels for long conversations, they fail to capture its dynamic evolution during ongoing interactions. Here, we present VizTrust, which addresses this challenge by introducing a real-time visual analytics tool that leverages a multi-agent collaboration system to capture and analyze user trust dynamics in human-agent communication. Built on established human-computer trust scales-competence, integrity, benevolence, and predictability-, VizTrust enables stakeholders to observe trust formation as it happens, identify patterns in trust development, and pinpoint specific interaction elements that influence trust. Our tool offers actionable insights into human-agent trust formation and evolution in real time through a dashboard, supporting the design of adaptive conversational agents that responds effectively to user trust signals.
@article{arxiv.2503.07279,
title = {VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication},
author = {Xin Wang and Stephanie Tulk Jesso and Sadamori Kojaku and David M Neyens and Min Sun Kim},
journal= {arXiv preprint arXiv:2503.07279},
year = {2025}
}