Algorithms for Finding Influential People with Mixed Centrality in Social Networks

Identifying the seed nodes in networks is an important task for understanding the dynamics of information diffusion. It has many applications, such as energy usage/consumption, rumor control, viral marketing, and opinion monitoring. When compared to other nodes, seed nodes have the potential to spread information in the majority of networks. To identify seed nodes, researchers gave centrality measures based on network structures. Centrality measures based on local structure are degree, semi-local, Pagerank centralities, etc. Centrality measures based on global structure are betweenness, closeness, eigenvector, etc. Very few centrality measures exist based on the network's local and global structure. We define mixed centrality measures based on the local and global structure of the network. We propose a measure based on degree, the shortest path between vertices, and any global centrality. We generalized the definition of our mixed centrality, where we can use any measure defined on a network's global structure. By using this mixed centrality, we identify the seed nodes of various real-world networks. We also show that this mixed centrality gives good results compared with existing basic centrality measures. We also tune the different real-world parameters to study the effect of their maximum influence.