Conference Proceedings
The International Conference on Emerging Technologies in Electronics, Computing and Communication 2022
(ICETECC`22)
Classification and Prediction of Spam Emails Based on AI Enabling Models Using Deep and Machine Learning Techniques
Junaid Mazhar Muhammad1*; Affan Bin Hasan1; Muhammad Farrukh Shahid1;| 1FAST-NUCES Karachi |
ABSTRACT
The increasing volume of unwanted/unsolicited bulk emails, also known as "SPAM," is a devastating issue that provokes a multitude of problems in communication systems. Over the past few years, the work on spam classification has been tremendously enhanced to a greater extent. In this paper, we present an approach that encompasses machine and deep neural network such as Gaussian Naive Bayes (GNB), Convolution Neural Networks (CNN) network, Long Short Term Memory (LSTM) network and a customised model developed with the combination of CNN and LSTM to classify and predict the widely used open source spam assassin dataset that contains around 6000 real email samples. The models are trained and tested, and the results are presented in the paper. Overall, CNN-LSTM attained a predication score of 98.68% on the spam dataset.