Finding influential users of web event in social media

Abstract

Users of social media have different influences on the evolution of a Web event. Finding influential users could benefit such information services as recommendation and market analysis. However, most of the existing methods are only based on social networks of users or user behaviors while the role of the contents contributed by users in social media is ignored. In fact, a Web event evolves with both user behaviors and the contents. This paper proposes an approach to find influential users by extracting user behavior network and association network of words within the contents and then uses PageRank algorithm and HITS algorithm to calculate the influence of users on the integration of two networks. The proposed approach is effective on several real-world datasets.