An Explainable Ensemble-Based Approach for Email Spam Detection

This research paper presents a machine learning-based approach for detecting spam emails using multiple classification algorithms including Naive Bayes, Logistic Regression, Support Vector Machine, Random Forest, XGBoost, and a stacked ensemble model. The dataset used in this study is a combination of the Enron Email Dataset and SMS Spam Collection Dataset. The data is preprocessed using techniques such as tokenization, stopword removal, and TF-IDF feature extraction. Experimental results show that the ensemble model achieves the highest accuracy of 97.7% and an F1-score of 0.979, outperforming individual models. Additionally, explainable AI techniques such as SHAP and LIME are used to interpret model predictions, making the system transparent, reliable, and suitable for real-world applications.