SMS Spam Classification Using Machine Learning Techniques
Tarun Jain, Payal Garg, Namita Chalil, Aditya Sinha, Vivek Kumar Verma, Rishi Gupta
Abstract
Almost every person today owns a mobile phone with at least the most basic facilities like messaging and calling. Spam calls are already infamous for the constant ringing of cell phones for promotional or fraudulent pitching to innocent customers. With the reducing costs of bulk messaging services from network providers, a massive base of these spam calls has shifted to messaging. SMS, standing for a short messaging service, has become a dumping ground of unwanted product descriptions and scam offers. Here, in this scenario, classification becomes a necessity. Classification in this context occurs as separating spam messages from ‘ham’ or legitimate messages. For this aforementioned purpose, we used natural language processing techniques and machine learning algorithms in this paper. We used four simple classification models on a dataset from UCI Machine Learning Repository. We compared the accuracies at the end, which pointed towards the most suitable model being SVM, with an accuracy of 98.797%.