Modeling and predicting cascading removal phenomenon over social networks

Innovations, opinions, ideas, recommendations or tendencies emerge in a variety of social networks. They can either disappear quickly or propagate and create considerable impact on the network. Their disappearance may also spread from one node to another across the network creating cascading behavior. Cascading phenomenon is mainly analyzed either by identifying the most influential nodes according to their features in the network, detecting quickly the phenomenon or targeting a minimum set of nodes that could maximize the spread of influence or minimize the propagation of a rumor or an outbreak. The objective of the present work is to predict the nodes to be deleted in cascade following the disappearance of one or many nodes. The cascading removal phenomenon is imitated by three well-known influence maximization cascading models in addition to two variants of a new cascading strategy which sound more consistent with human intuition over cascading removals. The prediction is done for an individual iteration of the cascading models, with the ability to be projected over the entire course of cascades without any loss of generality. We compare the prediction accuracy over three real-life networks and five synthetically generated schemas that imitate real social networks.