Investigating How Text and Motion Style Shape Directness In Embodied Conversational Agents

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Embodied Conversational Agents (ECAs) are becoming more widely used for various applications, notably in health. Some studies have demonstrated the effectiveness of delivering Motivational Interviews (MIs), a patient-centred behaviour change method, with ECAs. Despite showing promise, the effect of agent communication style on MI effectiveness remains underexplored. Directness has been shown to impact satisfaction and preference of dialogue systems, and effectiveness in some cases. However, outside of verbal style, how to control directness in ECAs to achieve these goals is not well understood. We designed an ECA to convey different levels of directness through language and Non-Verbal behaviours (NVBs), then evaluated the impact of language and NVB on directness with a perception study. The results showed that language influenced perceived directness, and that NVB contributed when aligned with indirect language. These findings suggest ways to shape conversational agents' communication style to enhance their effectiveness.

Original languageEnglish
Title of host publicationProceedings MIG 2025 - 18th ACM Conference on Motion, Interaction and Games
EditorsRobert W. Sumner, Fabio Zund, Sophie Jorg, Nuria Pelechano
PublisherAssociation for Computing Machinery (ACM)
ISBN (Electronic)9798400722363
DOIs
Publication statusPublished - 2 Dec 2025
Event18th Annual ACM SIGGRAPH Conference on Motion, Interaction, and Games, MIG 2025 - Zurich, Switzerland
Duration: 3 Dec 20255 Dec 2025

Publication series

NameProceedings MIG 2025 - 18th ACM Conference on Motion, Interaction and Games

Conference

Conference18th Annual ACM SIGGRAPH Conference on Motion, Interaction, and Games, MIG 2025
Country/TerritorySwitzerland
CityZurich
Period3/12/255/12/25

Keywords

  • Communication Style
  • Embodied Conversational Agents
  • Human-Avatar Interaction
  • Human-Computer Interaction
  • Motivational Interviewing
  • Non-Verbal Behaviour
  • Text Style Control

Fingerprint

Dive into the research topics of 'Investigating How Text and Motion Style Shape Directness In Embodied Conversational Agents'. Together they form a unique fingerprint.

Cite this