Abstract

Information propagation in the network is probabilistic in nature; simultaneously, it depends on the connecting paths of the propagation. Selection of seed nodes plays an important role in determining the levels and depth of the contagion in the network. This paper presents a comparative study when seed nodes for information propagation are selected through the properties of different centrality measures in the social network. This study captures the interaction measures of nodes in the social network, selects seed nodes based on five centrality measures, i.e. degree distribution, betweenness centrality, closeness centrality, Eigenvector and PageRank, and compares the affected nodes and levels of propagation within the network. We demonstrate the performance of the different centrality measures by processing three datasets of social network: Twitter network, Bitcoin network and author collaborative network. For the propagation of the information, we use breadth-first search (BFS) and susceptible–infectious–recovered (SIR) model and a detailed comparative study is also presented for each of the seed nodes selected using aforementioned network properties. Results show that the Eigenvector centrality and PageRank centrality measures outperform other centrality measures in all test cases in terms of propagation level and affected nodes during information propagation. Both Eigenvector and PageRank network data processing required a high computational overhead. For this reason we propose a hybrid model where using k-core the network is degenerated into a smaller network and centrality nodes are extracted from the smaller network. These centrality nodes, as compared to original centrality nodes, perform almost in the same manner in terms of influence maximization when k is chosen in a rational way.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call