Publicado em: 06/03/2012

Tese de Doutorado em Inteligência Artificial

UNIVERSIDADE FEDERAL DO RIO GRANDE DO SUL

INSTITUTO DE INFORMÁTICA

PROGRAMA DE POS-GRADUAÇÃO EM COMPUTAÇÃO

———————————————————

DEFESA DE TESE DE DOUTORADO

Aluna: Michelle Denise Leonhardt Camargo
Orientadora: Profa. Dra. Rosa Maria Viccari
Orientadora cotutela: Profa. Dra. Sylvie Pesty -Université de Grenoble (França)
Título: Enhancing Affective Communication in Embodied Conversational Agents Through Personality-Based Hidden Conversational Goals
Linha de Pesquisa: Inteligência Artificial
Data: 13/03/2012
Hora:10h
Local: Sala 220 (conselhos). Prédio 43412 – Instituto de Informática

Banca Examinadora:
Prof. Dr. Eliseo Berni Reategui – UFRGS – PPGIE
Prof. Dr. Dominique Duhaut – VALORIA
Profa. Dra. Márcia Cristina Moraes – PUCRS
Prof. Dr. Patrick Reignier – INRIA
Presidente da Banca: Profa. Dra. Rosa Maria Viccari

Abstract:
Embodied Conversational Agents (ECAs) are intelligent software entities with an em- bodiment used to communicate with users, using natural language. Their purpose is to exhibit the same properties as humans in face-to-face conversation, including the ability to produce and respond to verbal and nonverbal communication. Researchers in the field of ECAs try to create agents that can be more natural, believ- able and easy to use. Designing an ECA requires understanding that manner, personality, emotion, and appearance are very important issues to be considered.
In this thesis, we are interested in increasing believability of ECAs by placing per- sonality at the heart of the human-agent verbal interaction. We propose a model relating personality facets and hidden communication goals that can influence ECA behaviors.
Moreover, we apply our model in agents that interact in a puzzle game application. We develop five distinct personality oriented agents using an expressive communication language and a plan-based BDI approach for modeling and managing dialogue according to our proposed model.
In summary, we present and test an innovative approach to model mental aspects of ECAs trying to increase their believability and to enhance human-agent affective commu- nication. With this research, we hope to improve the understanding on how ECAs with expressive and affective characteristics can establish and maintain long-term human-agent relationships.

Keywords: Artificial Intelligence, Cognitive Systems, Embodied Conversational agents, believability