Understanding Service Integration of Online Social Networks: A Data-Driven Study

摘要: The cross-site linking function is widely adopted by online social networks (OSNs). This allows a user to link her account on one OSN accounts other OSNs. Thus, users are able sign in with the linked accounts, share contents among these and import friends from them. It leads service integration of different not only provides convenience for manage OSNs, but also introduces usefulness OSNs that adopt function. In this paper, we investigate based users’ data collected popular called Medium. We conduct thorough analysis its graph, find brought crosssite change Medium’s graph structure attract large number new users. However, almost none would become high PageRank (PageRank used measure user’s influence an OSN). To solve problem, build machine-learning-based model predict Medium their Twitter only. achieves F1-score 0.942 area under curve (AUC) 0.986. Based it, design system assist identify well-established through