Android-Based Short Message Service Filtering using Long Short-Term Memory Classification Model

Short Message Service (SMS) is a technology for sending messages in text format between two mobile phones that support such facility. Despite the emergence of many messaging applications, SMS still finds its use communication among people and broadcasting by governments providers. users often receive from parties, particularly marketing business purposes, advertisements, or elements fraud. Many those are irrelevant fraudulent spam. This research aims at developing android-based applications enable filtering Bahasa Indonesia. We investigate 1469 data classify them into three categories: Normal, Fraudulent, Advertisement. The classification method long short-term memory (LSTM) model TensorFlow. LSTM suitable because it has cell states architecture useful storing previous information. feature applicable on sequential as texts every word constructs form to complete sentence. observation results show accuracy level 95%. then integrated an Android-based application execute real-time classification.