Information Flow Detection and Tracking on Web2.0 BLOGS Based on Social Networks

Blogs have become a typical online publication in Web2.0 era. The users of blogs interact with each other by publishing entries, reading and posting comments to other's entries, and discussing with friends. By these actions, information propagates from user to user on the social networks. This paper extracts the information flow hidden in entries and investigates the rules of information flow in both temporal and spatial dimensions. A new approach for information flow detection and tracking on blogs has been proposed by using both social features and text features. The proposed approach has been evaluated through experiments using large scale of real data collected from SOHU blogs. The results demonstrate that our approach is more effective in Web2.0 blogs. The rules of information flow have also been investigated by analyzing the results, which in turn proves the necessity of using social features for information detection and tracking on blogs.