A study of graph simulation methodologies for synthetic Covert Social Network
In recent days terrorism poses a threat to homeland security. The major problem faced in network analysis is to automatically identify the key player who can maximally influence other nodes in a large relational covert network. The existing centrality based and graph theoretic approach are more concerned about the network structure rather than the node attributes. In this paper an unsupervised framework SoNMine has been developed to identify the key players in 9/11 network using their behavioral profile. The behaviors of nodes are analyzed based on the behavioral profile generated. The key players are identified using the outlier analysis based on the profile and the highly communicating node is concluded to be the most influential person of the covert network. Further, in order to improve the classification of a normal and outlier node, intermediate reference class R is generated. Based on these three classes the most dominating feature set is determined which further helps to accurately justify the outlier nodes.