Available from: psu.edu
[show abstract] [hide abstract]
ABSTRACT: Automatic text classifying is an import application of the information processing technology. This paper introduces the key techniques of Chinese text categorization such as text preprocessing, feature selection, feature representation, training and classifying algorithm, especially analyses the current most important several feature selection methods with emphasis. A Chinese text classifier based on KNN algorithm was developed. The system can preferably implement Chinese automatic text categorization and has a higher quality. We also use this classifier to compare several feature selection methods. In the end, we utilize the experiment results to prove the importance role of feature selection in text categorization.
Wireless Communications, Networking and Mobile Computing, 2007. WiCom 2007. International Conference on; 10/2007