Hot Topic Detection in News Blog

Topic detection in news blogs needs to carefully arrange the information and analyze the characteristics of topics. However, there are some difficulties for hot topic detection in blogs. On one hand, information overload and dynamic change of web pages are obstacles of information arrangement. On the other hand, there are different hotness evaluation norms for web topics. The proposed method first analyzes the characteristics of the news blog and recognizes the factors which can influence the evolution of a topic. Then a word network is constructed, and candidate topics are extracted from the word network based on the complex networks theory. Finally, hot topics in the news blog are identified by measuring the user participation, opinion communication between users and user forgetting degree.