Social network information diffusion model based on user’s influence and interesting

Abstract

A new non-topological information diffusion model of social network was proposed,called non-topological influence-interest diffusion model (NT-II).Representation learning was exploited to construct two hidden spaces for NT-II，called the user-influence space and the user-interest space,each user and each propagation item was mapped into a vector in space.The model predicted the probability of a user receiving a propagated item,considering not only the degree of influence from other users,but also the user's preference for propagated item.The experimental results show that the model can simulate the propagation process and predict the propagation results more accurately.

Keywords

• diffusion model;representation learning;user-influence space;user-interest space