An Improved Feature Selection for Categorization Based on Mutual Information

Authors:
Haifeng Liu;Zhan Su;Zeqing Yao;Shousheng Liu
Affiliations:
Institute of Sciences, PLA University of Science and Technology, Nanjing, China 210007;Institute of Sciences, PLA University of Science and Technology, Nanjing, China 210007;Institute of Sciences, PLA University of Science and Technology, Nanjing, China 210007;Institute of Sciences, PLA University of Science and Technology, Nanjing, China 210007
Venue:
WISM '09 Proceedings of the International Conference on Web Information Systems and Mining
Year:
2009

Citing 2
Cited 0

Toward Integrating Feature Selection Algorithms for Classification and Clustering

IEEE Transactions on Knowledge and Data Engineering
A novel feature selection algorithm for text categorization

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

The feature reduction is one of the core techniques in text categorization. But there is no consideration of text position factor to the differentiation of labeling text capability in the method of weighting basing on multi-information (MI) in features. So in this paper, we put forward an improved feature selection method that based on MI. By adding the amending parameters in different positions, we have increased the using efficiency about the character information. The result of experiment shows that this method has improved the accuracy of the text classification.