Modelling Empathy in Social Robotic Companions Iolanda Leite 1 , Andr´ e Pereira 1 , Ginevra Castellano 2 , Samuel Mascarenhas 1 , Carlos Martinho 1 , and Ana Paiva 1 1 INESC-ID and Instituto Superior T´ ecnico, Technical University of Lisbon, Portugal 2 HCI Centre, School of Electronic, Electrical and Computer Engineering University of Birmingham, United Kingdom iolanda.leite@ist.utl.pt Abstract. Empathy can be broadly defined as the ability to under- stand and respond appropriately to the affective states of others. In this paper, we present a scenario where a social robot acts as a chess compan- ion for children, and describe our current efforts towards endowing such robot with empathic capabilities. A multimodal framework for modeling some of the user’s affective states that combines visual and task-related features is presented. Using this model of the user, we personalise the learning environment by adapting the robot’s empathic responses to the particular preferences of the child who is interacting with the robot. We also describe a preliminary study conducted in this scenario. Keywords: social robots, empathy, affective user modeling, adaptive interaction. 1 Introduction Emotions shape how we appraise the environment and our attitudes towards other people and tasks. Isen and Reeve [21] reported that positive affect in- fluences people’s intrinsic motivation, enjoyment and performance of enjoyable tasks. Conversely, while experiencing negative emotions, people tend to judge their environment and future events more negatively [24]. A growing amount of research studies the relations between emotions and learning. For example, stu- dents in a positive mood are more willing to dedicate more effort in a problem solving task [18]. In a study using an intelligent tutoring system, Craig et al. [12] found that learning correlates negatively with boredom and positively with flow [13]. Other studies showed that a positive student-teacher relationship increases student’s trust, cooperation and motivation during the learning process, which can ultimately improve the learning experience [35]. In the last few years, there has been a growing interest in developing animated pedagogical agents with the aim of guiding the students through the learning environment while trying to keep them in a positive affective state [28]. Several studies suggest that pedagogical agents positively affect the way students per- ceive the learning experience due to their non-verbal behaviours [28], physical L. Ardissono and T. Kuflik (Eds.): UMAP 2011 Workshops, LNCS 7138, pp. 135–147, 2012. c  Springer-Verlag Berlin Heidelberg 2012