Different PCA scenarios for email filtering. Issue 1 (2nd January 2016)

• Record Type: Journal Article
• Authors: Dagher, Issam; Antoun, Rima
• Is Part Of: International journal of computers and applications. Volume 38:Issue 1(2016)
• Page Start: 41
• Page End: 54
• Publication Date: 2016-01-02
• Subjects: Ham -- Spam -- PCA -- SVM -- Bayes; Computers -- Periodicals; Computer software -- Periodicals; Computer networks -- Periodicals; Multimedia systems -- Periodicals; Internet -- Periodicals; World Wide Web -- Periodicals; Minicomputers -- Periodicals; Microcomputers -- Periodicals; 004.05
• DOI: 10.1080/1206212X.2016.1218237
• Languages: English
• ISSNs: 1206-212X

Abstract

Abstract: Improving email filtering (Ham vs. Spam emails) is a very important process. The objective of this paper is to increase the filtering accuracy and to decrease the processing time. It discusses different scenarios for Principal Component Analysis-Document Reconstruction (PCADR) classifier implemented for email filtering process The study highlights on the variation in the accuracy of a PCADR classifier with respect to the variation in feature preprocessing. Four scenarios were considered: Scenario 1: Ham and Spam classes are represented with different features. Scenario 2: Ham and Spam classes are represented with same features. Scenario 3: Ham and Spam classes are represented with common terms. Scenario 4: Ham and Spam classes are represented with common Features and Characteristic terms. Different experiments were done using a public corpus extracted from the University of California-Irvine Machine Learning Repository. Different training and test sets were used. A comparison of PCADR with Support Vector Machine and Bayes detector was done to prove its superior behavior.