@inproceedings{7082e2e2ca9e4d9f8f6b651d9b2546c5,
title = "Design of text categorization system based on SVM",
abstract = "This paper introduces the design of a text categorization system based on Support Vector Machine (SVM). It analyzes the high dimensional characteristic of text data, the reason why SVM is suitable for text categorization. According to system data flow this system is constructed. This system consists of three subsystems which are text representation, classifier training and text classification. The core of this system is the classifier training, but text representation directly influences the currency of classifier and the performance of the system. Text feature vector space can be built by different kinds of feature selection and feature extraction methods. No research can indicate which one is the best method, so many feature selection and feature extraction methods are all developed in this system. For a specific classification task every feature selection method and every feature extraction method will be tested, and then a set of the best methods will be adopted.",
keywords = "Feature extraction, Feature selection, SVM, Text categorization, VSM",
author = "Zhenyan Liu and Weiping Wang and Yong Wang",
year = "2012",
doi = "10.4028/www.scientific.net/AMR.532-533.1191",
language = "English",
isbn = "9783037854389",
series = "Advanced Materials Research",
pages = "1191--1195",
booktitle = "Materials Science and Information Technology II",
note = "2012 2nd International Conference on Materials Science and Information Technology, MSIT 2012 ; Conference date: 24-08-2012 Through 26-08-2012",
}