A new genetic-based rumor diffusion model for social networks

The spreading process of rumor is different from that of general messages because two special factors: reason of individual and rumor refuting, affect the process of rumor dissemination besides conventional factor, i.e. information amount. In this paper, we propose a genetics-based rumor diffusion model (GRDM) which regards an individual with multiple rumors in a network as a ‘chromosome’ which is composed by a set of genes. The GRDM specifies a rule for interactions between chromosomes to model the rumor interactions between individuals. A series of experiments are done on the dynamic social network dataset collected from Sina-Weibo with 9299 users and 215386 pieces of following relationship information between them. The experimental results show that the genetic-algorithm-based rumor diffusion model is reasonable and feasible in demonstrating the diffusion of rumor in social networks and some key factors, i.e. starting node, individual reason and rumor refuting, would affect the propagation process.