Survey of SMS Spam Detection Techniques: A Taxonomy

Short Message Service (SMS) spam remains a significant threat to users and businesses, with spammers constantly adopting more sophisticated techniques. This paper comprehensively surveys SMS spam detection methods, categorizing existing approaches into five primary groups: rule-based methods, traditional machine learning techniques, deep learning models, hybrid models, and ensemble methods. Each category is examined in detail, highlighting its strengths, limitations, and evolution. Rule-based methods, though historically significant, are limited by their inability to handle new or evolving spam tactics. Traditional machine learning techniques, such as Naive Bayes and support vector machines (SVM), offer improved accuracy but depend on handcrafted features. In contrast, deep learning models, including recurrent neural networks (RNN) and convolutional neural networks (CNN), excel in feature extraction and adaptability yet face challenges with model complexity and the need for large labeled datasets. Hybrid and ensemble methods combine the benefits of various models to improve performance, reduce bias, and enhance robustness. This review aims to provide a structured overview of the state of SMS spam detection, identify emerging trends, and suggest future research directions, including improving generalization, reducing data dependency, and exploring the integration of contextual information. The findings underscore the need for continued innovation to address the evolving landscape of SMS spam.