Novel Email Spam Classification using Integrated Particle Swarm Optimization and J48

E-mails have become an integral part of both private and professional lives and can also be studied as formal papers in communication between users. Several activities such as spam detection and classification, subject classification, etc. can be done by email’s data mining and analysis. Review has shown that the use of unsupervised filtering to filter the input data set is ignored by the most of the existing researchers. The use of hybridization of data mining techniques is ignored in order to improve the accuracy rate further for detection of fraudulent emails. Most of the existing techniques are limited to some significant features of emails therefore utilising more features may provide more significant results. The overall objective of this work is to propose an integrated particle swarm optimization based J48 algorithm to enhance the accuracy rate further.