PSEISMIC: A personalized self-exciting point process model for predicting tweet popularity

摘要

Social networking websites allow users to create and share a variety of items. Big information cascades of post resharing can be generated because users of these sites reshare each other's posts with their friends and followers. In this work, we aim at predicting the final number of reshares for any given post. We build on the theory of self-exciting point processes to develop a statistical model, PSEISMIC, which leads to accurate predictions of popularity. Moreover, we perform cluster analysis to group all tweets so that the coefficient of memory kernel in PSEISMIC can be estimated for every cluster, rather than using the same memory kernel. Experiments conducted on a large-scale retweet dataset show that the proposed PSEISMIC model outperforms the state-of-the-art approach, SEISMIC in predicting the popularity of a given post.