Automated Spam Email Identification Using Data Visualization and Machine Learning Techniques

Spam emails are a critical cyber challenge as they contribute to loss of productivity and security breaches.In this paper, we introduce an Artificial Neural Network (ANN)-based spam classifier using visualizationmethods for enhanced explainability. We use the SpamAssassin datasets for preprocessing the text data,TF-IDF feature extraction, and training an ANN classifier. Our model has an accuracy of 99.91%, alongwith a near-optimal F1-score of 1.00. In addition, we present visualization methods like a confusion matrixheatmap and graphs to facilitate better user comprehension of the performance of classification. Thefindings show the possibility of ANN-based classifiers integrated with visualization methods for enhancedspam filtering. Future research will explore integrating transformer-based models like BERT for improvedspam classification accuracy.