Abstract
1- Introduction
2- Related works
3- Problem formulation and methodology
4- Empirical study
5- Conclusions
References
Abstract
The identification of top persuaders from social networking websites is increasingly attracting attention because they can significantly affect consumers’ purchasing decisions in electronic word-of-mouth (eWOM) marketing. Existing studies on the identification of top persuaders have mainly focused on the idea of trust and have not considered distrust. However, this omission may lead to a high negative impact of the top persuaders identified from trust networks. To address this issue in the context of mixed trust networks, this study formulates the top persuader identification problem and develops a novel approach to identifying top persuaders. The structural properties of mixed trust networks are investigated through four measures: the degree of distribution, the correlation coefficient of trust and distrust, the cumulative distribution of the ratio between the degree of distrust and the degree of trust, and the mix pattern. To adapt to the context of mixed trust networks, a mixed trust PageRank (MTPR) index is conceived to evaluate the influential power of a top persuader. Reinforced by the dimensions of trust and distrust, the MTPR-based approach is proposed to identify top persuaders in mixed trust networks. The experimental results using real-world data collected from Epinions show that the proposed approach outperforms the degree centrality approach and the PageRank approach.
Introduction
In the digital era, Internet-based social communication services (e.g., Twitter, MySpace, Facebook, and LinkedIn) have resulted in the emergence of social persuasion as a complex force that governs the propagation of influence in online social networks (OSNs) [1–3]. Social persuasion is closely related to social contagion and network diffusion, by which a consumer’s attitude, belief, or behavior is influenced by other consumers in an OSN [4]. This phenomenon has allowed various companies to identify top persuaders who can propagate social influence through their high network status in OSNs and who have the ability to affect the behavior and attitudes of other consumers [5–7]. Therefore, the ability to discover top persuaders in an OSN has become critical to companies in electronic word-of-mouth (eWOM) marketing [8– 10]. In this context, marketing information can be diffused faster and be promoted better by top persuaders to their followers in OSNs via word of mouth.