CSR: A community based spreaders ranking algorithm for influence maximization in social networks

Online social networks have become a consistent part of our day-to-day life. They virtually connect people around the world and serve as ideal platforms for interactions, sharing of information, ideas, and products. Influence maximization (IM) is the problem of maximizing the reach of an idea or an opinion in a network by shortlisting the most influential nodes in the respective network, which are further used as seed nodes to spread the information in the rest of the network. It is a problem of great relevance in today’s world because of its real life applicability in the business. Numerous methods have been proposed in the literature to rank the nodes according to their spreading ability and certain other characteristics. In this paper, we propose a novel method to solve the problem of influence maximization named Communities based Spreader Ranking (CSR), which is based on the notions of communities and bridge nodes. It identifies bridge nodes as influential nodes based on three concepts: community diversity, community modularity, and community density. Community diversity is used to identify bridge nodes and the rest two are used to identify significant communities. Extensive experimentation validation on various datasets using popular information diffusion models demonstrates that the proposed method delivers proficient results compared to numerous previously known contemporary influence maximization methods.