Study on Topic Tracking System Based on SVM

Author

Li, Shuping ; Zhao, Jie ; Song, Zhichao ; Li, Shengdong

Author_Institution

Dept. of Comput. Sci., Mudanjiang Normal Univ., Mudanjiang, China

fYear

2011

fDate

8-9 Oct. 2011

Firstpage

83

Lastpage

87

Abstract

Text classification is the key technology for topic tracking, and vector space model (VSM) is one of the most simple and effective model for topics representation. Feature selection algorithm in VSM is an important means of data pre-processing, and it can reduce vector space dimension and improve the generalization ability of the algorithm. So we develop a topic tracking system based on SVM to study how feature dimension and the value of K-neighbors affect topic tracking. Then we get the variation law that they affect topic tracking, and add up their optimal values in topic tracking. And finally we analyze topic tracking system performance according to TDT evaluation results to find the reasons for this results.

Keywords

generalisation (artificial intelligence); pattern classification; support vector machines; text analysis; data preprocessing; feature dimension; feature selection algorithm; generalization; support vector machines; text classification; topic representation; topic tracking system; vector space model; Classification algorithms; Computers; Educational institutions; Support vector machine classification; Text categorization; Training; svm; tdt evaluation; topic tracking; weight of evidence for text;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge Acquisition and Modeling (KAM), 2011 Fourth International Symposium on

Conference_Location

Sanya

Print_ISBN

978-1-4577-1788-8

Type

conf

DOI

10.1109/KAM.2011.30

Filename

6137584