Skip to Main Content
In recent years, centroid-based document classifiers receive wide interests from text mining community because of their simplicity and linear-time complexity. However, the traditional centroid-based classifiers usually perform less effectively for Chinese text categorization. In this paper, we tackle the problem by developing a new way to calculate the class-specific weights for each term in the training phase; in the testing phase, the new documents are assigned to the centroid to which the document is most similar based on the weighted distance measurement. The experimental results demonstrate that the accuracy of our algorithm outperforms the traditional centroid-based classifiers, as well as outstanding efficiency compared with the Support Vector Machine (SVM) based classifiers for Chinese text categorization.