A Comparative Study of Classification Algorithms on Spam Detection

Abstract

We are going to explore on how the elaboration of text messages in all communication and transactions which are all taking place through web based tool known as email. Spam is an alternative way of an electronic messaging system to send a large number of messages to the user inbox. Here we are going to experiment many data mining techniques to the dataset of spam in an attempt to search the most suitable classifier to text message classification as spam and non-spam. Here we are going to check the performance of many classifiers with the use of feature selection algorithm and we found that in the result analysis part the Random Forest classifier provides finer accuracy with respect to other four classifiers such as Naive Bayes, Support vector machine(SVM), Logistic Model and Decision Tree