Email Spam Detection using Recurrent Neural Network

Abstract

Email is one of the mobile communication services that allows easy and inexpensive communication. Producing unwanted messages with the aim of advertising or harassment and sending these messages on Email have become the biggest challenge in this service. Various methods have been presented to detect unsolicited short messages; many of which are based on machine learning. Neural Networks have been applied to separate the unwanted text messages known as spam from normal short messages known as ham in Email. To the best of our knowledge, Recurrent Neural Network (RNN) has not been used in this issue yet. In this paper, we proposed a new method which utilizes RNN to separate the ham and spam with variable length sequences, even though we used a fixed sequence length. The proposed method, indicates a considerable improvement compared to Support Vector Machine SVM, token-based SVM and Bayesian algorithms.  There are two main types of methods to detect unwanted EMAIL: techniques along with user participation and content-based methods. Methods based on user participation are based on feedback from users and sharing their experiences. Because of the problems associated with data access and user experience, these methods are rarely used, but content-based methods act based on content analysis of text messages and are more common.