New Words Recognition Algorithm and Application Based on Micro-Blog Hot

New word identification is one of the difficult problems of Chinese information processing. In order to improve the efficiency of new word recognition, this paper proposed a new method to identify new word based on micro-blog message´s characteristic. First of all, the micro-blog message is segmented by using N-Gram, then we filter the candidate strings to obtain the candidate words, finally we construct an objective function based on characteristics of micro-blog message to identify new word. Compared with other new word identification methods, the experimental results show that the method proposed in this paper can significantly improve the effect of Chinese new word identification.