Email Spam Detection using Naive Bayes Algorithm Optimized with Particle Swarm Optimization

Email Spam Detection using Naive Bayes Algorithm Optimized with Particle Swarm Optimization

Singareddy Harsha Vardhan Reddy, Yanamalamanda Lakshmi Narasimha, Nandanavanam Bhanu Thahera, Vemulapalli Harsha

RVR&JC CE,

Guntur, A.P India

Abstract — Spamming through emails has always been one of the most exploited methods for the fraudsters. Spam emails are inappropriate and unwanted messages usually sent to breach security. Spam emails encompass various forms, including advertisements, commercial segments, as well as false promises of prices, discounts, or job opportunities. spammers continuously adapt their strategies to increase the chances of their emails bypassing filters and being opened by recipients. To overcome this issue we present a sophisticated approach for machine learning algorithm with Optimization to detect spam emails.A machine learning based Na¨ıve Bayes (NB) algorithm by using Particle Swarm Optimization (PSO). Naive Bayes is effective for email spam detection due to its ability to handle high-dimensional data (like text) and its simplicity, making it efficient even with large datasets. The performance of Na¨ıve Bayes algorithm is compared with the Support Vector Machine (SVM) using metrics such as accuracy, precision, recall, and F1-score.

Keywords—spam emails, Machine Learning, Naive Bayes, Particle Swarm Optimization, Support Vector Machine