Research on the performance of segmentation of text classification based on CNICC

With the development of Internet, people have entered the era of New Media, and the demand for intelligent information is more intense. How to make news industry, provide more personalized and efficient service for all walks of life, is something worth exploring. In this paper, we aim to analyze the performance of segmentation, which is the foundation of text classification. Our study describes the method of creating a type thesaurus about news based on Chinese news information classification and code. Experimental results show that the approach is a valid and promoted method of segmentation optimization in news classification.