• Vinay V. Duble

Due to the massive production of mobile phones in today’s world, the rate of growth of the number of its users has increases as well. In this scenario either cases in SMS or message traffic are brought into that spam. In addition, spamming has gone beyond the Inboxes of mobile phones to conquer the spammer’s quest. If the spam mail appears to have relevant benefits, is classified as spam. The hackers try to send spam messages for their financial or business benefits like market growth, lottery ticket information, and credit card information. Our approach involves the collection and preprocessing of a various dataset of SMS messages, comprising both spam and ham messages. A comparative analysis of various machine learning algorithms, including (SVM), Naive Bayes, and different types of naive Bayes, is conducted to identify the most effective model for Short Message Service (SMS) spam detection. Furthermore, the research explores the integration of natural language processing (NLP) techniques to capture contextual information and improve the accuracy of the spam filtering system. The proposed model undergoes rigorous evaluation using standard metrics such as precision, recall, and F1-score, demonstrating its effectiveness in differentiating between spam and legitimate SMS. The dataset is split into two categories for training and testing the research. Our experimental results have shown that our NB model outperforms previous models in spam detection with a 90% accuracy rate.

SMS Spam Detection Machine Learning Natural Language Processing (NLP) Spam Messages Ham Messages Feature Extraction Comparative Analysis Support Vector Machine (SVM) Naive Bayes XGBoost Random Forest Spam Classification Dataset Imbalance Accuracy Precision Recall F1 Score Text Preprocessing Exploratory Data Analysis (EDA) UCI Machine Learning Repository Performance Metrics Deep Learning Long Short-Term Memory (LSTM) BERT (Bidirectional Encoder Representations from Transformers) Spam Filtering

"Enhanced SMS Spam Detection Using Machine Learning and Natural Language Processing Techniques: A Comparative Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 11, page no.e791-e796, November-2024, Available :http://www.jetir.org/papers/JETIR2411489.pdf

"Enhanced SMS Spam Detection Using Machine Learning and Natural Language Processing Techniques: A Comparative Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 11, page no. ppe791-e796, November-2024, Available at : http://www.jetir.org/papers/JETIR2411489.pdf