Persuasion driven influence analysis in online social networks

Abstract

It is now a fact as well as a trend that people are increasingly relying on online social networks to work, study, and share with others. Thus, it is unavoidable for us to be influenced by others through online social networking. Studying social influence and information diffusion in online social networks can be remarkably useful in various real-life applications, notably influencer marketing and viral marketing. The Topical Affinity Propagation (TAP) model has been demonstrated with success to analyze the social influence on topic level. It manages to identify the most influential nodes on a given topic in social networks successfully. While TAP mainly focuses on the topic factor, it considers little about the complex relationship between individuals, which is crucial in calculating the influence probabilities between nodes. In this paper, the idea of quantitatively estimating the peer influence probability from a social persuasion perspective in sociology is exploited and consequently a persuasion-driven social influence analysis model is presented. Based on the TAP model and the social persuasion influence propagation measures, both the topical information and the persuasion influences between individuals are taken into consideration such that a social persuasion-driven influence analysis model is proposed. The experimental results on different data sets show that the social influences on a given topic can be discovered effectively by the proposed approach, especially under consideration of authority, the accuracy in identifying the most influential nodes can be significantly improved as compared with an existing work.