Discovering and Ranking Influential Users in Social Media Networks Using Multi-Criteria Decision Making (MCDM) Methods

Background: Social media networks created highly interactive platforms through which individuals and communities share, discuss, collaborate. It is important to discover and rank the influential users. Methods: In an online social media customers or users trust the opinion of other known customers or users, especially those with prior experience of a product or service, rather than company suggestions or recommendations. In a dynamic business situation, a customer or user in an e-commerce site like Amazon tends to trust the buying experiences of his/her known friends rather than the buying recommendations from Amazon. Findings: This paper provides a comprehensive study of various Multi-Criteria Decision Making (MCDM) methods to understand or discover and rank influential users in an online social media network such as Facebook. Experiment results were demonstrated using tradition metrics such as Page Rank, Betweenness and Closeness centrality measures and compared with MCDM based methods. It is proved that MCMD based methods are precise, dynamic and capable of identifying or ranking the influence users preciously than the standard benchmarked traditional metrics. Applications/Improvements: A well-managed campaign with influential users, enterprises can get sustainable profit or growth rather than doing generalized campaign on their product or services. Our experimental performance results can be compared with benchmark results.