TY - GEN
T1 - VizTrust
T2 - 2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025
AU - Wang, Xin
AU - Jesso, Stephanie Tulk
AU - Kojaku, Sadamori
AU - Neyens, David M.
AU - Kim, Min Sun
N1 - Publisher Copyright: © 2025 Copyright held by the owner/author(s).
PY - 2025/4/26
Y1 - 2025/4/26
N2 - 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 VizTrust1, 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.
AB - 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 VizTrust1, 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.
KW - Agentic System
KW - Conversational Agents
KW - Large Language Model
KW - Machine Learning
KW - Natural Language Processing
KW - Visualization Analysis
UR - https://www.scopus.com/pages/publications/105005731157
U2 - 10.1145/3706599.3719798
DO - 10.1145/3706599.3719798
M3 - Conference contribution
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI EA 2025 - Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
Y2 - 26 April 2025 through 1 May 2025
ER -