Privacy-preserved community discovery in online social networks

Community detection is a pivotal task for understanding user behaviors in online social networks, in which a third-party server can partition the users with close social relationships and similar behaviors into a same group. The existing approaches for community detection usually request full access to detailed social connections among users, which are usually sensitive. How to derive a meaningful community structure while not disclosing sensitive information remains unsettled. In this work, a novel framework is proposed to discover community structure in online social networks while preserving sensitive link information. The framework takes both social connections and users’ published contents into consideration. It also provides the flexibility in which a third-party server can adaptively select the concerned subgraph. The experiment results towards a real world dataset show that the proposed framework outperforms the baseline algorithm and can achieve a high accuracy on the discovered community structure.