Noname manuscript No. (will be inserted by the editor) Human Interaction Discovery in Smartphone Proximity Networks

Abstract Since humans are fundamentally social be-ings and interact frequently with others in their daily life, understanding social context is of primary impor-tance in building context-aware applications. In this pa-per, using smartphone Bluetooth as a proximity sensor to create social networks, we present a probabilistic ap-proach to mine human interaction types in real life. Our analysis is conducted on Bluetooth data continuously sensed with smartphones for over one year from 40 in-dividuals who are professionally or personally related. The results show that the model can automatically dis-cover a variety of social contexts. We objectively vali-dated our model by studying its predictive and retrieval performance.