Legitimate and spam SMS classification employing novel Ensemble feature selection algorithm

The classification of Short Message Service (SMS) is a crucial task that requires distinguishing undesirable and harmful messages from legitimate ones. These spam messages may include malicious links that reveal users' personal data to some sharp practices. Many Machine Learning (ML) and deep learning algorithms prevail for spam detection. However, a large number of features present in the message drop the classifier's performance, which can be untangled through feature engineering. This paper proposes an ensemble feature selection algorithm assessed over a high-dimensional imbalanced dataset that resembles the actual data prevailing in the surroundings. The proposed work employs wrapper-based Stratified K-fold Cross-Validated (SKCV) Recursive Feature Elimination with Cross-Validation (RFECV) over hyperparameters tuned Support Vector Classifier (SVC) and random forest algorithms. This study contributes an efficient feature selection algorithm that produces a pruned feature subset substituting the whole dataset. To establish the potential of the proposed approach, its performance is evaluated against five feature selection techniques, including Mutual Information (MI), Low Variance (LV), Particle Swarm Optimization (PSO), Chi-square, and Recursive Feature Elimination (RFE). All obtained feature subsets are analyzed with three ML models Logistic Regression (LR), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGB). This research also compares the proposed framework results with Long Short Term Memory (LSTM) neural network to validate its competence.