Performance Evaluation of Email Spam Text Classification Using Deep Neural Networks

Abstract

Spam in email box is received because of advertising, collecting personal information, or to indulge malware through websites or scripts. Most often, spammers send junk mail with an intention of committing email fraud. Today spam mail accounts for 45% of all email and hence there is an ever-increasing need to build efficient spam filters to identify and block spam mail. However, notably today’s spam filters in use are built using traditional approaches such as statistical and content-based techniques. These techniques don’t improve their performance while handling huge data and they need a lot of domain expertise, human intervention and they neglect the relation between the words in context and consider the occurrence of the word. To address these limitations, we developed a spam filter using deep neural networks. In this work, various deep neural networks such as RNN, LSTM, GRU, Bidirectional RNN, Bidirectional LSTM, and Bidirectional GRU are used to a built spam filter. The experimentation was carried out on two datasets, one is a 20 newsgroup dataset, which contains multi-classes with 20,000 documents and the other is ENRON, a dataset contains 5,000 emails. The custom-designed models have performed well on both benchmark datasets and attained greater accuracy.