A Comparative Study on Spam Identification using Naive Bayes and SVM

Email is one of the most frequently employed digital means of communication among individuals use on an on-going basis. Sending unidentified messages to someone is termed as spam. The internet remains the most accessible source of information, and social media is becoming more and more prevalent. This research offers a unique framework that uses multinomial naive bayes (multinomial NB) and support vector machine (SVM) advanced machine learning approaches to improve email spam detection. It increases the classification efficiency and accuracy when compared to more conventional techniques like Random Forest and basic Naive Bayes. The method also includes a significant amount of data preprocessing, including text normalization, stemming, and count vectorization feature extraction. This approach can be enhanced by being utilized by email clients or servers to recognize spam emails. Experiments have demonstrated that the Support Vector Machine technique returns good accuracy, and this research advances email spam detection techniques.