Improving Linear Classifier for Chinese Text Categorization

Abstract

In this paper we increase the number of representatives for each class to compensate for the potential weakness of linear classifier which compute one representative for each class. To evaluate the effectiveness of our approach, we compared with linear classifi- er produced by Rocchio algorithm and the k-Nearest Neighbor(kNN) classifier. Experimental results show that our approach improved linear classifier and achieved microaveraged accuracy similar to that of k- Nearest Neighbor(kNN), with much less classi fication time. Furthermore, we could provide a suggestion to reorganize the structure of classes when identify new representatives for linear classifier.