Trust Repair in Human-Agent Teams: the Effectiveness of Explanations and Expressing Regret
conference paper
Trust is a fundamental aspect of teamwork in Human-Agent Teams (HATs). Trust violations are an inevitable aspect of the cycle of trust, so effective trust repair strategies are needed to ensure durable and successful team performance. This study explores the effectiveness of four trust repair strategies. In a first-person shooter resembling HAT task, a trust violation was provoked when the robotic agent failed to detect an approaching enemy. After this, the agent offered an apology composed of an explanation and/or an expression of regret (either one alone, both or neither). Our results indicated that expressing regret was crucial for effective trust repair, and that trust repair was most effective when the apology contained both components. © 2022 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Topics
TNO Identifier
973204
ISSN
15488403
ISBN
9781713854333
Publisher
International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Source title
Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022, 9 May 2022 through 13 May 2022
Pages
1944-1946
Files
To receive the publication files, please send an e-mail request to TNO Repository.