Abstract
As information spreads across social links, it may reach different people and become cascades in social networks. However, the elusive micro-foundations of social behaviors and the complex underlying social networks make it very difficult to model and predict the information diffusion process precisely. From a different perspective, we can often observe the interplay between information diffusion and the cascade structures. On one hand, information driven by different mechanics may evolve into diverse structures; On the other hand, different cascade structures will reach different groups people and thus affect the diffusion process. In this paper, we explore the relationships between information diffusion and the cascade structures in social networks. By embedding the cascades in a lower dimensional space and employing spectral clustering algorithm, we find that the cascades generally evolve into five typical structure patterns with distinguishable characteristics. In addition, these patterns can be identified by observing the initial footprints of the cascades. Based on this observation, we propose to predict cascade growth with the structure patterns. The experiment results show that the accuracy of predicting both the structure and virality of cascades can be improved significantly.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.