Spam Email Classification Using Meta-heuristic Algorithms

Abstract

Email communication has grown much in recent decades owing to its low cost, ease of use, speed, and utility across a wide range of content, including online news channels, social media, and political news. Spam messages are an email that is sent to a large number of persons, group discussions, or associations without their consent or knowledge. In the long run, it harms email system usability as it becomes a more destructive component of email traffic. As a result, email systems become sluggish and time-consuming to operate, as well as using a large amount of bandwidth and storage space. Spam may also disseminate harmful and objectionable material on the internet. The feature selection approach is an essential task in text analysis and message categorization, and the use of meta-heuristic algorithms are one of the best approaches. This chapter introduces a novel method for spam message identification using the horse herd optimization technique. The algorithm inputs become opposition-based and then multi-objective as a consequence of this change in structure. Spam identification, a discrete and multi-objective issue, is the final use for this algorithm. The results indicate that the proposed method also performs better than other methods.