Observing Behaviors of Information Diffusion Models for Diverse Topics of Posts on VK

The way information spreads through society has changed significantly over the past decade with the advent of online social networking. It is also observed that users have distinct behaviors, i.e., the topics of conversations shared among users, based on which social media platforms they use. However, many previous approaches for predicting information spreading in social networks do not consider this versatility. In this paper, we examine Independent Cascade (IC) information diffusion model which assumes that each node independently influences its neighboring nodes. We show the results of applying IC model to the biggest Russian social network Vkontakte (VK). We first apply the model to synthetic networks and compare the results with the real networks extracted for different topics. The results supports our hypothesis that the behavior of information diffusion in social media is different based on the topics shared. Our results also show that IC model does not properly describe the diffusion processes in VK.