Intelligent Detection of Mobile SMS Spam via Machine Learning and Deep Learning

The global rise in social media usage has led to a surge in unwanted bulk SMS, necessitating the development of an effective system to filter out these messages. The most prevalent issue on the internet is spam text messages. Sending a spam-filled SMS is a straightforward task for spammers. Spammers are able to take valuable data, including contacts and files, from our devices. In recent years, several word embedding techniques leveraging deep learning have been developed. These advancements in word representation could offer a reliable remedy for these problems This study will look at a technique that employs natural language processing to distinguish among spam and ham texts utilizing the SMS Spam Collection Dataset from the UCI Machine Learning Repository. We compared the accuracy and outcomes of using the Bi-LSTM and LSTM. The effectiveness of the dataset is assessed using measures like F1-score, recall, and accuracy. The study demonstrates that the dataset's overall accuracy increases when Bi-LSTM classification is used. Python is used for all work, and a Jupyter notebook is used for implementation.