Efficient algorithm for finding the influential nodes using local relative change of average shortest path

Abstract

In complex networks, finding the influential nodes playing a crucial role in theoretical and practical point of view because they are capable of propagating information to large portion of the network. Investigating the dynamics of information spreading in complex networks is a hot topic with a wide range of applications, including information dissemination, information propagation, rumour control, viral marketing, and opinion monitoring. In recent years, several centrality measures have been discovered to find influential nodes in complex networks. In this work, the local relative change of average shortest path (i.e Local RASP) based on the local structure of the network is being proposed. This local RASP measure of a node defined based on the local network’s relative change in average shortest path when the node is deleted. Our local RASP centrality produces good results compared to degree, betweenness, closeness, semi-local, PageRank, Trust-PageRank, and RASP centralities. Our local RASP centrality measure’s computation time is less compared to global centrality measure RASP. It measures the information diffusion efficiently within the network through the initial seed nodes identified by the local RASP.