Research of automatic tagging method in news with statistical language model

With the development of the network and the wide application of the related technologies, the boundaries between the new media and the traditional media are gradually blurred. As a new way of information classification, label has gradually come to most people's attention. In this paper, we present a news automatic tagging method. The method can be used to change the rigid and conservative structure of the traditional classification and gives the tagging right of the resources to users, who can define the resources more flexibly and accurately. This paper makes in-depth analysis on news content. Using the traditional information recommendation technology, we integrate the generative theory model with the news automatic tagging method. Thus, we propose a method for news automatic tagging based on language model. Finally, we validate our strategy's performance in label tagging through experiment.