Security and Communication Networks
Group affinity based social trust model for an intelligent movie recommender system
Multimedia Tools and Applications
| Hi-index | 0.00 |
The emergence of large-scale online social networks has attracted much interest in recent years, and the structure of online social networks has been rigorously studied in the last few years. However, to date, only selected silos of fragmented online social networks have been investigated. This is due to the lack of information about the people who participate in several online social networks. However, recently, the evolution of portable social environment makes it possible to mine the global social graph of collective online social networks. Hence, in this paper, we study the structure of the global social graph as a hybrid hypergraph, where the hyperedges connect a user’s multiple identities distributed over several local social graphs. Based on our empirical study using the Social Graph API, we show that (1) the population of websites and the degree distribution of hyperedges follow the power-law, and that (2) the existence of connectors, who participate in several online social networks, ensures that the global social graph is not fragmented but interconnected. We believe that these findings can shed a new light on the design of future systems based on decentralized social networks, with a bird’s-eye view of the global social graph.