Title :
Feature Weighting Scheme for Text Categorization Based on Rough Set
Author :
Lican, Huang ; Xin, Xu ; Yuhong, Zhao ; Junzhou, Gao
Author_Institution :
Coll. of Inf. & Electron., Zhejiang Sci-Tech Univ., Hangzhou, China
Abstract :
Feature weighting is an important issue in text categorization. In this paper we analyze the characteristics of rough set theory and TF-IDF, and propose a feature weighting scheme for text categorization by applying approximation accuracy and approximation quality in variable rough set model. The decision information of a feature for categorization is introduced into the weight, which reflects the importance of the feature.
Keywords :
rough set theory; text analysis; TF-IDF; approximation accuracy; approximation quality; feature weighting scheme; rough set theory; text categorization; Accuracy; Approximation methods; Classification algorithms; Feature extraction; Set theory; Text categorization; Training; approximation accuracy; approximation quality; feature weighting; rough set; text categorization;
Conference_Titel :
Networking and Distributed Computing (ICNDC), 2010 First International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4244-8382-2
DOI :
10.1109/ICNDC.2010.46
