Spam SMS Classification
Ms. Akshara Prachi, Mrs. Ankita Gandhi, Mr. Garv Kavdia, Mr. Deepak Parmar · International Journal of Research Publication and Reviews · 2025
Spam SMS messages pose a significant security and privacy risk to the users, and therefore effective detection methods are needed.Spam messages normally bear malicious links, phishing, or unwanted advertisements, and hence filter mechanisms need to be established.The present work focuses on creating an NLP-based machine learning spam classifier.The studies examine various classification models, e.g., Naïve Bayes, Support Vector Machines (SVM), and Random Forest, how their performance with respect to accuracy, precision, recall, and F1-score.Our model is implemented using Python libraries such as Scikit-learn, Pandas, NumPy, and NLTK, and automation using Selenium for dataset collection.The results indicate that our model achieves an accuracy of 97%, which significantly improves spam detection efficiency.The results indicate that appropriate preprocessing, model choice, and feature extraction are crucial in spam classification.Future work will emphasize incorporating deep learning methods and cloud deployment to further enhance system performance.