Performance Evaluation of Meta-data features for Spam SMS Classification using Sequential Models

The escalating threat of cybercrime, particularly in the form of spam, fraudulent messages, and phishing attacks, poses a substantial risk to individuals who may unknowingly divulge sensitive information to malicious user. This paper addresses the urgent need for a robust spam filtering model capable of detecting and preventing these deceptive messages before reaching users’ inboxes or SMS folders. Focusing on the English spam SMS dataset from the UCI repository, we propose a sequential learning-based spam message filtering framework using the meta-data feature of SMS message. The performance of the meta-data features are compared with the various other methods such as vectorization, sequential model with embedding layers. Performance shown that the Meta-data feature vectors doesn’t depend on any parameters for the process of vectorization and it leverages the performance of the sequential models.