Sylvie Pesty

PERSEED: A Self-Based Model of Personality for Virtual Agents Inspired by Socio-cognitive Theories

Consistency and coherence in behaviors are key concepts for creating believable virtual agents. Personality is described by psychology as a set of stable and individualized behaviors. Thus, endowing agents with a personality can help agents to exhibit consistent behaviors. In this paper, we suggest using a socio-cognitive perspective to build a model of personality for virtual agents and to highlight some of the personality structures and processes. Because many researchers in personality psychology emphasize the role of the self in personality, we propose PERSEED, a conceptual model of personality that is based on self-regulation theories.

Towards a conversational language for artificial agents in mixed community

Present agent and interaction (agent communication language: ACL) models have been conceived for pure artificial agent communities, most often strongly linked with knowledge exchange. But these models are not adapted to conversational interactions, and particularly to mixed community melting artificial and human agents. We first underline these model limitations. We propose a first step towards a conversational agent language fitting with a BDI agent model in respect with Speech Acts Theory and integrating essential elements of the conversational background. This proposition is a continuation of Chaib-draa and Vandervekens work [1] on a recursive semantics for ACL according to the situation calculus.

Inferring Peer-Related Emotions in a Collaborative Learning Game

This paper presents an affective model to infer student’s emotions in a collaborative learning game. The model is focused on the representation and recognition of emotions closer to the collaboration dynamics (e.g., pride, shame, admiration and reproach). Consistently to a cognitive approach, the student’s emotions are represented and inferred by modeling the student’s cognitive appraisal of interactions praiseworthiness, evaluated according to her/his standards. The affective student model relies on Bayesian Networks, through which the causal dependencies among student’s personality traits, goals, behavioral standards, interactions and emotions are mapped. A collaborative testbed game that provides simple interaction mechanisms was implemented. Using the testbed game, students can construct shared solutions of a class of logical problems. The cognitive and affective variables of the model and their probabilistic relationships are detailed and the capture of interaction evidence from the testbed game is discussed.