Enhancing Spam Detection Using Hybrid of Harris Hawks and Firefly Optimization Algorithms

Abstract

Email spam is a significant challenge that negatively affects communication and data security. Machine Learning (ML) is a widely adopted approach for spam detection. However, the large amount of spam data can degrade ML models performance. To address this issue, this paper proposes a novel feature selection method that combines the Firefly Optimization Algorithm (FOA) and Harris Hawks Optimization (HHO) to enhance the effectiveness of ML models in spam detection. The proposed method was evaluated using the ISCX-URL2016 dataset with several classifiers. Hyperparameters for these classifiers were optimized using the Grid Search technique to ensure the best possible performance. The achieved results indicate that the Extra Trees (ET) classifier, when combined with the novel FOA and HHO-based feature selection method, achieved the highest accuracy of 99.83%, outperforming all other tested classifiers. This demonstrates the potential of our approach in significantly improving spam detection systems by effectively handling large-scale spam data.