Content-based Approach for Vietnamese Spam SMS Filtering

Short Message Service (SMS) spam is a serious problem in Vietnam because of the availability of very cheap pre-paid SMS packages. There are some systems to detect and filter spam messages for English, most of which use machine learning techniques to analyze the content of messages and classify them. For Vietnamese, there is some research on spam email filtering but none focused on SMS. In this work, we propose the first system for filtering Vietnamese spam SMS. We first propose an appropriate preprocessing method since existing tools for Vietnamese preprocessing cannot give good accuracy on our dataset. We then experiment with vector representations and classifiers to find the best model for this problem. Our system achieves an accuracy of 94% when labelling spam messages while the misclassification rate of legitimate messages is relatively small, about only 0.4%. This is an encouraging result compared to that of English and can be served as a strong baseline for future development of Vietnamese SMS spam prevention systems.