Hybrid Email Spam Detection Model Using Artificial Intelligence

Douzi, Samira; AlShahwan, Feda A.; Lemoudden, Mouad; El Ouahidi, Bouabid

Abstract

The growing volume of spam Emails has generated the need for a more precise anti-spam filter to detect unsolicited Emails. One of the most common representations used in spam filters is the Bag-of-Words (BOW). Although BOW is very effective in the classification of the emails, it has a number of weaknesses. In this paper, we present a hybrid approach to spam filtering based on the Neural Network model Paragraph Vector-Distributed Memory (PV-DM). We use PV-DM to build up a compact representation of the context of an email and also of its pertinent features. This methodology represents a more comprehensive filter for classifying Emails. Furthermore, we have conducted an empirical experiment using Enron spam and Ling spam datasets, the results of which indicate that our proposed filter outperforms the PV-DM and the BOW email classification methods.

Citation

Douzi, S., AlShahwan, F. A., Lemoudden, M., & El Ouahidi, B. (2020). Hybrid Email Spam Detection Model Using Artificial Intelligence. International Journal of Machine Learning and Computing, 10(2), 316-322. https://doi.org/10.18178/ijmlc.2020.10.2.937

• Journal Article Type: Article
• Publication Date: 2020-02
• Deposit Date: Feb 28, 2023
• Publicly Available Date: Feb 28, 2023
• Journal: International Journal of Machine Learning and Computing
• Peer Reviewed: Peer Reviewed
• Volume: 10
• Issue: 2
• Pages: 316-322
• DOI: https://doi.org/10.18178/ijmlc.2020.10.2.937
• Keywords: Spam, deep learning, word2vec, bag of word