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

2025-03-10

AI Summary

This study addresses the challenge of fine-grained modeling and responsive adaptation to dynamic user trust in real-time human-AI dialogue. We propose VizTrust, the first system to enable real-time, four-dimensional trust quantification—grounded in competence, integrity, benevolence, and predictability—via multi-agent collaborative perception, trust-scale-driven signal extraction, temporal modeling of interaction logs, and an explainable visualization dashboard. VizTrust supports millisecond-level trust state tracking, interaction-level attribution analysis, and automatic generation of context-aware adaptation strategies. In multi-turn dialogue experiments, it achieves 92.3% event attribution accuracy, significantly improving both trust perception fidelity and adaptive responsiveness of conversational agents. Our work establishes the first end-to-end paradigm for real-time trust analytics and adaptive intervention in trustworthy human-AI collaboration.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• Measures dynamic user trust in human-AI communication.
• Captures real-time trust evolution during interactions.
• Identifies interaction elements influencing trust formation.

Innovation

• Real-time visual analytics for trust dynamics
• Multi-agent system captures evolving user trust
• Dashboard provides actionable trust insights