Email Spam Behavioral Sieving Technique using Hybrid Algorithm

Email spam filtering is a critical task in today's digital world due to the significant increase in the volume of spam emails. To address this issue, various machine learning (ML) and statistical techniques have been proposed to classify spam and ham emails accurately. This research study proposes a hybrid algorithm that combines two techniques: The Naive Bayes (NB) and the Support Vector Machine (SVM). The proposed algorithm first preprocesses the email data by removing stop words, stemming, and transforming the text data into a numerical format. Then, the NB algorithm is used to extract the relevant features from the email data. The extracted features are then fed into the SVM algorithm, which uses a nonlinear kernel function to classify the emails. The methods were tested on two datasets: PU, Lingspam. The experimental results show that the proposed hybrid algorithm outperforms the standalone NB and SVM algorithms in terms of precision, and recall.In conclusion, the proposed hybrid algorithm is an effective approach for email spam filtering, and it can be used by email service providers to filter out spam emails from their users' inboxes.