Detection Phishing E-Mails Using Feature Analysis and Ensemble Learning

Phishing emails are sent by thousands of phishers who attempt to trick a user into believing that the email is from someone they know or trust in order for them to take some sort of action upon opening it. Despite the development of techniques for detecting phishing emails, phishers are continuously creating new strategies by using social engineering methods or employing persuasive or coercive language to manipulate users into complying with their requests. This paper has proposed a filter that can examine the content of messages based on two feature analysis methods sentiment analysis using VADER and TF-IDF text vectorization. these features are combined and used as input for Naive Bayes, SVM, and Random Forest classifiers. These classifiers are integrated into the ensemble model. The experimental results of the weighted average ensemble model on four standard datasets achieved accuracy of 99.51%, precision 99.49%, recall 99.29% and F1 score 99.39%.