Litcius/Paper detail

An Effective Spam Message Detection Model using Feature Engineering and Bi-LSTM

Antony L Rosewelt, Naveen D Raju, Sannasi Ganapathy

20222022 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)23 citationsDOI

Abstract

In today's digital era, the unwanted messages are communicated with many people and attack their device through the messages. Spammers steal the secret data of the users that are stored in their mobile device and also creates huge loss to the end user. The various spam detection techniques are proposed by many researchers in the past. Even though, no technique achieved the required detection accuracy. For fulfilling the current user requirements, this paper proposes an effective classifier that combines the Vectorization based Feature Engineering process and Bidirectional Long Short-Term Memory (Bi-LSTM) for detecting the spam in short text message (SMS). The proposed method applies feature engineering process for identifying useful features and also perform effective data pre-processing using vectorization and also perform classification using Bi-LSTM. The proposed method is evaluated by conducting experiments and proved as better than other methods in terms of precision, recall, f1-measure and detection accuracy.

Topics & Concepts

Computer scienceFeature engineeringVectorization (mathematics)Artificial intelligenceFeature (linguistics)Classifier (UML)Process (computing)Feature extractionPrecision and recallMobile deviceData miningMachine learningDeep learningPattern recognition (psychology)World Wide WebParallel computingLinguisticsPhilosophyOperating systemSpam and Phishing DetectionNetwork Security and Intrusion DetectionText and Document Classification Technologies
An Effective Spam Message Detection Model using Feature Engineering and Bi-LSTM | Litcius