A new fast entropy‐based method to generate composite centrality measures in complex networks

Abstract

Summary Determining the centrality of nodes in complex networks provides practical benefits in many areas such as detecting influencer nodes, viral marketing, and preventing the spread of rumors. On the other hand, there is no consensus for the definition of centrality. Therefore, different centrality measures such as degree, closeness, and betweenness have been developed to measure the centrality of a node. However, each centrality measure highlights the various characteristics of the nodes in the network from its own point of view. This causes each centrality measure to rank the nodes in a different order. In recent years, researchers have focused on approaches that combine multiple centrality measures. Thus, the perspectives of different centrality measures can be considered simultaneously. In this study, we have proposed a fast and efficient method using the analytic hierarchy process and entropy weighting to combine multiple centrality measures. We tested the proposed method with synthetic and real datasets and compared the results with those of state‐of‐the‐art methods. The experimental results showed the proposed method to be competitive with these advanced methods, whereas it performed much better than the other methods in terms of computational speed. This indicated that our proposed method could be applied to large and dynamic complex networks.

Estimating the Expected Influence Capacities of Nodes in Complex Networks under the Susceptible-Infectious-Recovered Model

“…However, many of the measures developed only considered the local and global impacts of the nodes [17]- [22] or network communities [18], [19], [23]- [25]. Recently, another approach has been adopted that combines multiple centrality measures to develop new hybrid centrality measures [26]- [34]. However, many of these studies ignore the dynamics of the propagation model.…”