Developing an Efficient Hybrid Approach for Email Spam Filtering: SPAM-NSGA-II-NvBys

Abstract

Any type of unwanted email that you didn't sign up to receive is considered spam. However, some spam could be a part of an identity theft scam or another type of fraud. Some spam is annoying but not unpleasant. In order to combat the spam phenomenon's ongoing growth, anti-spam filters have recently become indispensable technologies for Internet service providers. E-mails are filtered inconsistently across different users nevertheless of the user’s curiosity. For statistically figuring out whether a specific email message is actually spam or not, there isn't one particular algorithm. To address this issue, we present a hybrid approach that combines the Navie Bayes spam filtering algorithm with the Multi objective Genetic Algorithm: Non-dominated Sorting Genetic Algorithm (NSGA-II), resulting in a better result in reducing spam mails entering the user's inbox. SPAM-NSGA-II-NvBys will be the name of our proposed hybrid approach. The filter's evaluation revealed that it can make decisions with high accuracy (96.24% in the worst case and 99.66% in the best case).