id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_x6fbaqa72nhnhazv3jeeoqz4ci	Wenqian Shang	A novel feature selection algorithm for text categorization	2007	5	.pdf	application/pdf	3500	459	67	A new measure function of Gini index is constructed and made to fit text categorization. show that our improvements of Gini index behave better than other methods of feature selection. Keywords: Text feature selection; Text categorization; Gini index; kNN classifier; Text preprocessing information gain, expected cross entropy, the weight of evidence of text, odds ratio, term frequency, mutual information, CHI (Yang & Pedersen, 1997; Mladenic & Grobelnik, index for text feature selection and weight-adjustment. Through deeply analyzing the principles of Gini index and text feature, we construct a new measure function of Gini index and use it to select features The performance of five feature selection measure functions on top 10 classes The performance of five feature selection measure functions on training set B The performance of five feature selection measure functions on training set B feature selection methods in text categorization.	./cache/work_x6fbaqa72nhnhazv3jeeoqz4ci.pdf	./txt/work_x6fbaqa72nhnhazv3jeeoqz4ci.txt