:In recent time, online social networks like, Facebook, Twitter, and other platforms, provide functionality that allows a chunk of information migrates from one user to another over a network. Almost all the actual networks exhibit the concept of community structure. Indeed overlapping communities are very common in a complex network such as online social networks since nodes could belong to multiple communities at once. The huge size of the real-world network, diversity in users profiles and, the uncertainty in their behaviors have made modeling the information diffusion in such networks to become more and more complex and tend to be less accurate. This work pays much attention on how we can accurately predicting information diffusion cascades over social networks taking into account the role played by the overlapping nodes in the diffusion process due to its belonging to more than one community. According to that, the information diffusion is modeled in communities in which these nodes have high membership for reasons that may relate to the applications such as market optimization and rumor spreading. Our experiment made on a real social data, Digg news aggregator network on 15% of overlapped nodes, using our proposed model SFA-ICBDM described in previous work. The experimental results show that the cascade model of the overlapped nodes whether represents seed or node within cascade achieves best prediction accuracy in the community which the node belongs at more
SLPA: Uncovering Overlapping Communities in Social Networks via a Speaker-Listener Interaction Dynamic Process
