Humans are social animals, they interact with different communities offriends to conduct different activities. The literature shows that humanmobility is constrained by their social relations. In this paper, weinvestigate the social impact of a person's communities on his mobility,instead of all friends from his online social networks. This study can beparticularly useful, as certain social behaviors are influenced by specificcommunities but not all friends. To achieve our goal, we first develop ameasure to characterize a person's social diversity, which we term `communityentropy'. Through analysis of two real-life datasets, we demonstrate that aperson's mobility is influenced only by a small fraction of his communities andthe influence depends on the social contexts of the communities. We thenexploit machine learning techniques to predict users' future movement based ontheir communities' information. Extensive experiments demonstrate theprediction's effectiveness.
展开▼
