Hierarchical E-mail Spam Filtering Using AI & Data Mining Techniques: Decision Tree, Support Vector Machine, Multilayer Perception, Naļve Bays, Bayesian Network, and Random Forests - Softcover

Khater, Ismail M.

Softcover

ISBN 10: 3847314130 ISBN 13: 9783847314134

Publisher: LAP LAMBERT Academic Publishing, 2012

Synopsis

Email spam continues to be a major problem in the Internet. With the spread of malware combined with the power of botnets, spammers are now able to launch large scale spam campaigns covering wide range of topics causing major traffic increase and leading to enormous economical loss. There have been great research efforts to combat email spam. However, a major problem in most email spam filters is that they may result in filtering some legitimate emails. Such a problem could be prohibitively expensive in practice especially if the misclassified email is of a great importance to the recipient. For this reason, it is important to build an email spam filter that is capable of efficiently filtering spam while minimizing collateral damage. Since header-based and content-based email spam filtering are the two main approaches for email spam filtering, we propose to combine both approaches (i.e., header-based and content-based) in such a way that achieve the best of both worlds. That is to build fast, efficient and highly accurate email spam classifier. In particular, we propose a Hierarchical E-mail Spam Filtering (HESF) system that is composed of two main phases.

About this title

About the Author

Ismail Khater is a lecturer at Birzeit University, Palestine. He received the MSc BSc in Computer Engineering from Jordan University of Science & Technology, Irbid, in 2011 and Birzeit University, Ramallah, in 2007, respectively. From Jul 2007 to Sep 2009, he worked as a teaching & research assistance at Birzeit University, He was born in 11Dec1983

Edition details

• Publisher: LAP LAMBERT Academic Publishing
• Publication date: 2012
• Language: English
• ISBN 10: 3847314130
• ISBN 13: 9783847314134
• Binding: Paperback
• Number of pages: 136