Abstract:

The Short Message Service (SMS) has been widely used as a communication tool over the past few decades as the popularity of mobile phone and mobile network grows. It allows for the broad spread of "spams," i.e., inferiority news with deliberately false information. The widespread spread of spams has the potential for very negative impacts on people and society. Machine Learning methods for anti-spam filters have been noticeably effective in categorizing spam messages. This paper presents, a novel approach for Supervised Machine Learning based SMS Spam Detection. Dataset used in this research is known as Tiago’s dataset. Crucial step in the experiment was data preprocessing, which involved reducing text to lower case, tokenization, removing stopwords. The SMS dataset used was imbalanced, and to solve this problem, we used oversampling and under-sampling techniques. The support vector Machine (SVM), Naïve Bayes (NB), and Logistics Regression (LR) are applied on the spam and ham SMS dataset. SMS spam filter inherits much functionality from E-mail Spam Filtering. Comparing the performance of various supervised learning algorithms we find the support vector machine algorithm gives us the most accurate result

Description:

Short Message Service (SMS), Spam Detection, Machine Learning