Empirical Study of Different Classifiers with Feature Empirical Study of Different Classifiers with Feature Empirical Study of Different Classifiers with Feature Empirical Study of Different Classifiers with Feature Extraction for E Extraction for E Extraction for E Extraction for E--Spam Filtering
Himadri Sekhar Atta · 2014
E-mail or electronic mail is a principal mode of communication for quite some time in both professional and personal use. But over the last few years email spam has rapidly increased. Several techniques have been adopted for spam filtering. Among the various approaches developed to eliminate spam, filtering is an important and popular one. In this paper, an empirical study is done using some email datasets. In the first step datasets were taken and various classifiers like naive bayes, SVM, k-NN and decision tree were implemented and the performances were observed. In the next level, the important features were extracted from the datasets and then performances of the classifiers were observed. The objective of this paper is to highlight the findings through the empirical study, which will also help us to determine a good classifier for spam filtering. It also illustrates the information regarding feature extraction and different classifiers.