VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication

1Binghamton University, New York, USA; 2Clemson University, South Carolina, USA; 3University of Hawaii at Manoa, Hawaii, USA
*Corresponding author

Accepted conference: ACM CHI Conference 2025 (acceptance rate: 32.83%)

DOI: 10.1145/3706599.3719798
Workflow of VizTrust
Workflow of VizTrust

Abstract

Trust plays a fundamental role in shaping the willingness of users to engage and collaborate with 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 respond effectively to user trust signals.

Video Presentation

Acknowledgements

We thank the reviewers for their constructive feedback on this research.

BibTeX

@inproceedings{wang2025viztrust,
  title={VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication.},
  author={Wang, Xin and Tulk Jesso, Stephanie and Kojaku, Sadamori and Neyens David M. and Kim, Min-Sun},
  booktitle={Extended Abstracts of the CHI Conference on Human Factors in Computing Systems},
  pages={1--10},
  year={2025}
}

If you have any questions, please feel free to contact Vision(Xin) Wang