Why don't you do what you said you would? Conversational strategies for agents to understand users' reasons in supporting behavior

Bibliographic Data

ID21452912
AuthorsPei‐Yu Chen (0000-0003-2793-2361, Delft University of Technology, corresponding author), Pei-Yu Chen (Delft University of Technology), M Birna van Riemsdijk (0000-0001-9089-5271, University of Twente), Dirk Heylen (0000-0003-4288-3334, University of Twente), Dirk K J Heylen (University of Twente), Catholijn M Jonker (0000-0003-4780-7461, Delft University of Technology), Myrthe L Tielman (0000-0002-7826-5821, Delft University of Technology)
Year2025
Pages1-20
Publication date2025-04-17
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueBehaviour and Information Technology (JOURNAL)
Journal identifiersISSN: 0144-929X • E-ISSN: 1362-3001
PublisherInforma UK Limited (PUBLISHER • GB)
DOI10.1080/0144929x.2025.2483793
OpenAlexW4409523802
LanguageEN
References cited55

Effective support from personal assistive technologies relies on accurate user models that capture user values, preferences, and context. Knowledge-based techniques model these relationships, enabling support agents to align their actions with user values. However, understanding values in a single context is insufficient due to the dynamic nature of behaviour. This study explores the use of dialogue strategies to update user models. Participants were randomly assigned to different strategies and they discussed one randomly chosen non-adherence situation with the agent. Then, their emotions, acquired information accuracy, completeness, and dialogue experience were rated. Our findings suggest that multiple-choice dialogues may limit response depth, reducing the perceived completeness of behaviour reasons. In contrast, open-ended questions allow more detailed input but require more time and effort, potentially worsening the dialogue experience. Through inductive coding, we identified key topics, such as individual challenges, priorities, tangible outcomes, and values, essential for constructing personalised user models. We also analyzed conversation paths to improve dialogue-based user model updates in support agents. Further research is needed to refine the relationship between dialogue strategies and self-conscious emotions, considering diverse backgrounds and health goals, while enhancing dialogue design

Internet privacy · World Wide Web · AI in Service Interactions · Computer Science · Psychology · Psychology of Social Influence · Social Robot Interaction and HRI

Tools

Open DOIOpen Access