HWSMCB: A community-based hybrid approach for identifying influential nodes in the social network

Abstract

Influence Maximization is concerned with identifying a set of influential nodes in the social network that aims to maximize the spread of information, disease, and influence. Such a set of nodes is responsible for optimizing the influence in the network and is NP-Hard problem. To address this issue, different centrality measures have been proposed such as betweenness centrality, closeness centrality, degree centrality, but all of them suffered from some drawbacks. Some recent research works found that the dynamics of the network are greatly affected by the group structure, which is an important topological property of the social network. This paper proposes a novel framework, named, a community-based hybrid approach for identifying influential nodes in the social network (HWSMCB), to deal with the influence maximization problem. A dynamic Weighted Sum Method (D-WSM), a multi-criteria decision making method (MCDM), is introduced to take into account the node’s topological features simultaneously. The proposed HWSMCB is based on D-WSM and exploits community structure to identify influential nodes from the underlying social network. To establish the efficacy of the HWSMCB, experiments are conducted on real-world networks under the SIR epidemic model. The results obtained from HWSMCB are compared with some competitive methods such as Hybrid community based approach using K-means(HKM), W-Topsis (WT), betweenness centrality, page rank, closeness centrality, and degree centrality based on two parameters: diffusion speed and diffusion quality.