In this talk I will present our research toward modeling socio-emotional behaviors for virtual agent, focusing on communicative acts, emotions, and social attitudes. I will cover the relation between mental states and nonverbal behaviors as well as their realization in an embodied conversational agent. I will also present an architecture that allows virtual agent to adapt to user’s nonverbal behaviors during a dyadic interaction. I will focus on three studies that look at different levels of adaptation mechanisms: conversational strategy, nonverbal behaviors, signals.
Catherine Pelachaud (CNRS-ISIR) is Director of Research in the laboratory ISIR, Sorbonne University. Her research interest includes embodied conversational agent, nonverbal communication (face, gaze, and gesture), expressive behaviors and socio-emotional agents. With her research team, she has been developing an open-source platform called Greta of an interactive virtual agent that can display emotional and communicative behaviors.