Intelligent virtual agents are being endowed with empathic behaviours to perform roles such as virtual therapists. Studies often evaluate the level of rapport established, but do not measure the therapeutic benefit and the relative advantage of empathic versus neutral behaviours. We have created two virtual (empathic/neutral) therapists. Our experiment with 63 participants consisted of one within-subjects (empathic/neutral) and one between-subjects (order) factors. Regardless of the virtual therapist used, improvements in baseline emotion were reported after the first interaction (time one) and further improvement after the second interaction (time two). Our study reveals that if the human initially expresses strong emotional feeling for a problem they are facing, rapport will be higher for the empathic therapist and the level of rapport established at the first meeting will persist regardless of whether the second encounter used empathic or neutral dialogue. Conversely, participants experiencing low emotional feeling reported greater rapport with the neutral therapist, and that level of rapport persisted in the second encounter with the alternative therapist. This study shows that an empathic agent will not necessarily build more rapport or deliver better emotional outcomes than a neutral agent. Further studies are needed to determine when tailoring and complex behaviours are justified.

Virtual agents that improve the lives of humans need to be more than user-aware and adaptive to the user’s current state and behavior. Additionally, they need to apply expertise gained from experience that drives their adaptive behavior based on deep understanding of the user’s features (such as gender, culture, personality, and psychological state). Our work has involved extension of FAtiMA (Fearnot AffecTive Mind Architecture) with the addition of an Adaptive Engine to the FAtiMA cognitive agent architecture. We use machine learning to acquire the agent’s expertise by capturing a collection of user profiles into a user model and development of agent expertise based on the user model. In this paper, we describe a study to evaluate the Adaptive Engine, which compares the benefit (i.e., reduced stress, increased rapport) of tailoring dialogue to the specific user (Adaptive group) with dialogues that are either empathic (Empathic group) or neutral (Neutral group). Results showed a significant reduction in stress in the empathic and neutral groups, but not the adaptive group. Analyses of rule accuracy, participants’ dialogue preferences, and individual differences reveal that the three groups had different needs for empathic dialogue and highlight the importance and challenges of getting the tailoring right.