Title :
Study on the Spam-Filtering System based on Feature Selection Mechanism and Improved SVM Classification
Author :
Liu, Shouqiang ; Qi, Deyu ; Liu, Bo ; Pan, Chunhua ; Yang, Bo
Author_Institution :
Coll. of Comput. Sci. & Eng., South China Univ. of Technol., Guangzhou
Abstract :
Spam mail is bombing and causing a great problem, while there is still no appropriate counter-measures. After discussing some spam-filtering systems, this paper brings forward a spam-filtering system based on feature selection mechanism and improved SVM classification, system design, realization and evaluation is discussed following. Performance measure and experimental results are proved to outperform other conventional systems
Keywords :
information filtering; support vector machines; unsolicited e-mail; feature selection; improved SVM classification; spam mail; spam-filtering system; Bayesian methods; Educational institutions; Electronic mail; Information filtering; Information filters; Knowledge based systems; Postal services; Support vector machine classification; Support vector machines; Text categorization;
Conference_Titel :
Computational Intelligence and Security, 2006 International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
1-4244-0605-6
Electronic_ISBN :
1-4244-0605-6
DOI :
10.1109/ICCIAS.2006.295442
