Topic Detection and Tracking Method for Tibetan Network

Abstract

Internet has become an important tool to gain information; how to effectively detect hot topics from a lot of network information sources, e.g., Tibetan network, seems to be an urgent issue. Traditional hot topic is mainly based on the number of comments to get and the topic contents are usually not considered. In this letter, we study the approach of content-based relevance, i.e., based on user browsing behavior and the topic attention degree to discover the hot topic. And use the complex network theory to analyze the tracking model.