Towards Analysis of Expressive Gesture in Groups of Users: Computational Models of Expressive Social Interaction Antonio Camurri, Giovanna Varni, Gualtiero Volpe Casa Paganini – InfoMus Lab, DIST – University of Genova Viale F. Causa 13, 16145 Genova, Italy www.infomus.org www.casapaganini.org antonio.camurri@unige.it, giovanna@infomus.org, gualtiero.volpe@unige.it Abstract. In this paper we present a survey of our research on analysis of expressive gesture and how it is evolving towards the analysis of expressive social interaction in groups of users. Social interaction and its expressive implications (e.g., emotional contagion, empathy) is an extremely relevant component for analysis of expressive gesture, since it provides significant information on the context expressive gestures are performed in. However, most of the current systems analyze expressive gestures according to basic emotion categories or simple dimensional approaches. Moreover, almost all of them are intended for a single user, whereas social interaction is often neglected. After briefly recalling our pioneering studies on collaborative robot- human interaction, this paper presents two steps in the direction of novel computational models and techniques for measuring social interaction: (i) the interactive installation Mappe per Affetti Erranti for active listening to sound and music content, and (ii) the techniques we developed for explicitly measuring synchronization within a group of users. We conclude with the research challenges we will face in the near future. Keywords: expressive gesture analysis and processing, analysis of social interaction in small groups, multimodal interactive systems. 1 Introduction This paper presents a survey of our research on analysis of expressive gesture and how it is evolving towards the analysis of social interaction in (small) groups of users. Research on expressive gesture became particularly relevant in recent years (e.g., see the post-proceedings of Gesture Workshops 2003, 2005, and 2007). Psychological studies have been a fundamental source for automatic analysis of expressive gesture since they identified which features are most significant (e.g., De Meijer, 1989; Wallbott, 1998; Boone and Cunningham, 1998). A further relevant source has been research in the humanistic tradition, in particular choreography. As a major example, in his Theory of Effort, the choreographer Rudolf Laban (1947) describes the most significant qualities of movement. Starting from these sources, several systems for analysis of expressive gesture were developed (e.g., Camurri et al., 2003, 2005; Kapur et al., 2005; Bernhardt et al., 2007).