GroupMe: Supporting Group Formation with Mobile Sensing and Social Graph Mining

Nowadays, social activities in the real world (e.g., meetings, discussions, parties) are more and more popular and important to human life. As the number of contacts increases, the implicit social graph becomes increasingly complex, leading to a high cost on social activity organization and activity group formation. In order to promote the interaction among people and improve the efficiency of social activity organization, we propose a mobile social activity support system called GroupMe, which facilitates the activity group initiation based on mobile sensing and social graph mining. In GroupMe, user activities are automatically sensed and logged in the social activity logging (ACL) repository. By analyzing the historical ACL data through a series of group mining (group extraction, group abstraction) algorithms, we obtain implicit logical contact groups. We then use the sensed contexts and the computed user affinity to her logical groups to suggest highly relevant groups in social activity initiation. The experimental results verify the effectiveness of the proposed approach.