Path prediction of information diffusion based on a topic-oriented relationship strength network

Abstract

Path prediction of information diffusion is helpful for early warning and monitoring of network public opinion. Previous research focused on collecting feature sets to predict netizens’ spreading behavior, and few of them went further into predicting information diffusion path cascade by cascade. To solve this problem effectively, we proposed a prediction method based on a topic-oriented relationship strength network. First, we analyzed a subset of historical interaction records and found the temporal correlations in interactive frequency and in interest topics between users. Second, we constructed a topic-oriented relationship strength network to indicate users’ spreading preferences, including frequency and interest. Third, we collected some features and applied machine learning models to predict information diffusion paths cascade by cascade in the network. The experimental results testified that our method could predict the information diffusion path effectively with fewer features. Moreover, our experimental network shows some interest communities and different roles of users in information diffusion.