WSEAS Transactions on Systems and Control
Print ISSN: 1991-8763, E-ISSN: 2224-2856
Volume 16, 2021
Evaluation of the Performance for Popular Three Classifiers on Spam Email without using FS Methods
Authors: , ,
Abstract: Email is one of the most economical and fast communication means in recent years;
however, there has been a high increase in the rate of spam emails in recent times due to the increased
number of email users. Emails are mainly classified into spam and non-spam categories using data
mining classification techniques. This paper provides a description and comparative for the
evaluation of effective classifiers using three algorithms - namely k-nearest neighbor, Naive
Bayesian, and support vector machine. Seven spam email datasets were used to conducted
experiment in the MATLAB environment without using any feature selection method. The
simulation results showed SVM classifier to achieve a better classification accuracy compared to the
K-NN and NB.
Search Articles
Pages: 121-132
DOI: 10.37394/23203.2021.16.9