AI-Based Spam Message Shield with WhatsApp Message Detection using NLP

Abstract: With the exponential growth of mobile communication, SMS spam has become one of the most prevalent security and privacy concerns. Spam messages lead to financial fraud, data theft, and reduced user experience. Detecting such messages using traditional rule-based systems has proven insufficient due to evolving spam patterns. This research paper presents a comprehensive study of SMS spam detection techniques using machine learning models such as Naïve Bayes, Support Vector Machines (SVM), Logistic Regression, and Deep Learning approaches. A mini- project implementation demonstrates the use of natural language processing (NLP) techniques, including tokenization, TF-IDF, stemming, and lemmatization. The study highlights dataset characteristics, feature engineering, model performance, comparative results, and implementation constraints. Findings show that ML-based classifiers significantly outperform rule-based systems, achieving accuracy above 95%. Future directions include hybrid deep learning models and real-time adaptive systems.

Keywords: SMS Spam Detection, Machine Learning, NLP, TF-IDF, Classification, Naïve Bayes, Logistic Regression.