A Cluster-Based Epidemic Model for Retweeting Trend Prediction on Micro-blog.

Tweets spread on social micro-blog bears some similarity to epidemic spread. Based on the findings from a user study on tweets' short-term retweeting characteristics, we extend the classic Susceptible-Infected-Susceptible SIS epidemic model for tweet's retweeting trend prediction, featured by the multiple retweeting peaks, retweeting lifetime, and total retweeting amount. We cluster micro-blog users with similar retweeting influence together, and train the model using the least square method on the historic retweeting datato obtain different groups' retweeting rates. We demonstrate its effectiveness on a real micro-blog platform.