Spam filtering using big data and deep learning

Spam e-mails and other fake, falsified e-mails like phishing are considered as spam e-mails, which aim to collect sensitive personal information about the users via network or behave against authority in an illegal way. Most of the e-mails around the Internet contain spam context or other relevant spam like context such as phishing e-mails. Since the main purpose of this behavior is to harm Internet users financially or benefit from the community maliciously, it is vital to detect these spam e-mails immediately to prevent unauthorized access to email users' credentials. To detect spam e-mails, using successful machine learning and classification methods are therefore important for timely processing of emails. Considering the billions of e-mails on the internet, automatic classification of emails as spam or not spam is an important problem. In this thesis, we studied supervised machine learning and specifically "deep learning" methods to classify emails. Our results indicate that deep learning is very promising in terms of successful classification of emails with an accuracy of up to 96%.