Sensing and Modeling Human Networks using the Sociometer

Knowledge of how people interact is important in manydisciplines, e.g. organizational behavior, social networkanalysis, information diffusion and knowledge managementapplications. We are developing methods to automaticallyand unobtrusively learn the social network structures thatarise within human groups based on wearable sensors. Atpresent researchers mainly have to rely on questionnaires,surveys or diaries in order to obtain data on physicalinteractions between people. In this paper, we show howsensor measurements from the sociometer can be used tobuild computational models of group interactions. Wepresent results on how we can learn the structure of face-to-face interactions within groups, detect when membersare in face-to-face proximity and also when they are havinga conversation.