Print Email Facebook Twitter Acquiring Semantic Knowledge for User Model Updates via Human-Agent Alignment Dialogues Title Acquiring Semantic Knowledge for User Model Updates via Human-Agent Alignment Dialogues Author Chen, P.Y. (TU Delft Interactive Intelligence) Tielman, M.L. (TU Delft Interactive Intelligence) Heylen, Dirk K.J. (University of Twente) Jonker, C.M. (TU Delft Interactive Intelligence; Universiteit Leiden) van Riemsdijk, M.B. (TU Delft Interactive Intelligence; University of Twente) Contributor Lukowicz, Paul (editor) Mayer, Sven (editor) Koch, Janin (editor) Shawe-Taylor, John (editor) Tiddi, Ilaria (editor) Date 2023 Abstract For personal assistive technologies to effectively support users, they need a user model that records information about the user, such as their goals, values, and context. Knowledge-based techniques can model the relationships between these concepts, enabling the support agent to act in accordance with the user's values. However, user models require updating over time to accommodate changes and continuously align with what the user deems important. In our work, we propose and investigate the use of human-agent alignment dialogues for establishing whether user model updates are needed and acquiring the necessary information for these updates. In this paper, we perform an exploratory qualitative focus group study in which we investigate participants' opinions about written examples of alignment dialogues, as a foundation for their design. Transcripts were analyzed using thematic analysis. A main theme that emerged concerns the potential impact of agent utterances on the user's feelings about themselves and about the agent. Subject Behaviour support technologyConversational agentsDialogueHuman-agent alignmentUser modellingValues To reference this document use: http://resolver.tudelft.nl/uuid:0ae6c2d6-5d75-4c62-b87e-d533302f5ce9 DOI https://doi.org/10.3233/FAIA230077 Publisher IOS Press ISBN 9781643683942 Source HHAI 2023: Augmenting Human Intellect - Proceedings of the 2nd International Conference on Hybrid Human-Artificial Intelligence Event 2nd International Conference on Hybrid Human-Artificial Intelligence, HHAI 2023, 2023-06-26 → 2023-06-30, Munich, Germany Series Frontiers in Artificial Intelligence and Applications, 0922-6389, 368 Part of collection Institutional Repository Document type conference paper Rights © 2023 P.Y. Chen, M.L. Tielman, Dirk K.J. Heylen, C.M. Jonker, M.B. van Riemsdijk Files PDF FAIA_368_FAIA230077.pdf 550.43 KB Close viewer /islandora/object/uuid:0ae6c2d6-5d75-4c62-b87e-d533302f5ce9/datastream/OBJ/view