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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Xin, Jesso, Stephanie Tulk, Kojaku, Sadamori, Neyens, David M, Kim, Min Sun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916648306343936
author Wang, Xin
Jesso, Stephanie Tulk
Kojaku, Sadamori
Neyens, David M
Kim, Min Sun
author_facet Wang, Xin
Jesso, Stephanie Tulk
Kojaku, Sadamori
Neyens, David M
Kim, Min Sun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication
Wang, Xin
Jesso, Stephanie Tulk
Kojaku, Sadamori
Neyens, David M
Kim, Min Sun
Human-Computer Interaction
Artificial Intelligence
Computation and Language
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.
title VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2503.07279