Groups make nodes powerful: Identifying influential nodes in social networks based on social conformity theory and community features

Abstract Identifying a group of influential nodes in social networks help us understand the hierarchical structure of the network and make a better control the spread of information. Moreover, it can offer guidance in avoiding the breakdown of the power system and the Internet, identifying drug targets and essential proteins. Undoubtedly, most of the influence measures suffer the low resolution. The same score corresponds to multiple nodes. What’s worse is that the effect of overlapping between nodes is not fully considered. It causes resource waste in node selection. The purpose of this paper is to identify a set of distributed nodes with the strong propagation ability. Inspired by the interplay between the individuals and groups from sociological and complex networks, we propose a node ranking method based on the social conformity theory and community feature based on VoteRank. This proposed method calculates the node influence capability from two points of view, one is the individual, the other is the group. From the point of the individual, it quantifies the attractive power of the nodes with the feature of their neighbors based on the theory of conformity. It can distinguish the nodes with the same degree and similar structure. From the other point, it measures the initiating power with the scale of the community and the relative location of the node. Furthermore, a node selection strategy based on information coverage and community tightness is proposed to solve the problem of overlapping. Finally, node attractive power, initiating power and the node selection strategy are combined to improve VoteRank. The experimental results on real-world networks show the effectiveness of our methods. The results also explains that the enormous energy from the groups makes the node powerful.