Outtweeting the twitterers - predicting information cascades in microblogs

摘要: Microblogging sites are a unique and dynamic Web 2.0 communication medium. Understanding the information flow in these systems can not only provide better insights into underlying sociology, but is also crucial for applications such as content ranking, recommendation filtering, spam detection viral marketing. In this paper, we characterize propagation of URLs social network Twitter, popular microblogging site. We track 15 million exchanged among 2.7 users over 300 hour period. Data analysis uncovers several statistical regularities user activity, graph, structure URL cascades dynamics. Based on results propose model that predicts which likely to mention URLs. The correctly accounts more than half mentions our data set, while maintaining false positive rate lower 15%.