@inproceedings{aa16c8f14eba440d9738956ef1024c58,
title = "A comprehensive comparative study on term weighting schemes for text categorization with support vector machines",
abstract = "Term weighting scheme, which has been used to convert the documents as vectors in the term space, is a vital step in automatic text categorization. In this paper, we conducted comprehensive experiments to compare various term weighting schemes with SVM on two widely-used benchmark data sets. We also presented a new term weighting scheme tf-rf to improve the term's discriminating power. The controlled experimental results showed that this newly proposed tf-rf scheme is significantly better than other widely-used term weighting schemes. Compared with schemes related with tf factor alone, the idf factor does not improve or even decrease the term's discriminating power for text categorization.",
keywords = "Categorization, SVM, Term weighting schemes, Text",
author = "Man Lan and Tan, \{Chew Lim\} and Low, \{Hwee Boon\} and Sung, \{Sam Yuan\}",
year = "2005",
doi = "10.1145/1062745.1062854",
language = "英语",
isbn = "1595930515",
series = "14th International World Wide Web Conference, WWW2005",
pages = "1032--1033",
booktitle = "14th International World Wide Web Conference, WWW2005",
note = "14th International World Wide Web Conference, WWW2005 ; Conference date: 10-05-2005 Through 14-05-2005",
}