Integrating Conversation Trees and Cognitive Models within an ECA for Aggression De-escalation Training.

T. Bosse, S. Provoost

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

Abstract

Traditionally, Embodied Conversational Agents communicate with humans using dialogue systems based on conversation trees. To enhance the flexibility and variability of dialogues, this paper proposes an approach to integrate conversation trees with cognitive models. The approach is illustrated by a case study in the domain of aggression de-escalation training, and a preliminary evaluation in the context of a practical application is presented.
Original languageEnglish
Title of host publicationPRIMA 2015: Principles and Practice of Multi-Agent Systems
Subtitle of host publication18th International Conference Bertinoro, Italy, October 26 – 30, 2015 Proceedings
EditorsQ. Chen, P. Torroni, S. Villata, J. Hsu, A. Omicini
PublisherSpringer
Pages650-659
Number of pages10
ISBN (Electronic)9783319255248
ISBN (Print)9783319255231
DOIs
Publication statusPublished - 2015

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume9387
ISSN (Print)0302-9743
NameLecture Notes in Artificial Intelligence
Volume9387

Cite this