Un modèle d'interlocuteur virtuel avec des comportements d'écoute crédibles

We present a computational model that generates listening behaviour for a virtual agent. It triggers backchannel signals according to the user’s visual and acoustic behaviour. The appropriateness of the backchannel algorithm in a user-agent situation of storytelling, has been evaluated by naïve participants, who judged the algorithm-ruled timing of backchannels more positively. The choice of the type and the frequency of the backchannels to be displayed is performed considering the agent’s personality traits. We link agents with a higher level of extroversion to a higher tendency to perform more backchannels than introverted ones, while linking neuroticism to less mimicry production and more response and reactive signals sent. We run a perceptive study to test these relations in agentuser interactions, as evaluated by third parties. MOTS-CLÉS : Agents conversationnels animés, comportements d'écoute, rétroactions, traits de personnalité, sélection de l'action.