Affiliations: [a] School of Computer Science and Technology, Anhui University, Hefei, China
| [b] School of Electronics and Information Engineering, Anhui Jianzhu University, Hefei, China
Abstract: Traditional artificial information processing and classification methods can not deal with large-scale information well, and there is a problem of low classification purity. In view of the above situation, a new text information classification method based on quadratic fuzzy clustering algorithm is proposed. Firstly, in the method, text preprocessing is carried out, including Chinese word segmentation and de stop words, then text feature selection is made, and vector space model is used to represent the text. Finally, based on the secondly fuzzy clustering algorithm, a classifier is constructed to achieve text information classification. The results show that: compared with the traditional artificial information processing and classification method, when using the method based on the secondly fuzzy clustering algorithm for text information classification, the F value is more than 90%, and the average purity is higher, which shows that the classification performance of this method is better.
Keywords: Preprocessing, text classification, feature selection, classifier
