A COMPARATIVE STUDY OF TRADITIONAL MACHINE LEARNING, DEEP LEARNING, AND TRANSFORMER-BASED MODELS FOR SPAM DETECTION: PERFORMANCE, FEATURE ANALYSIS, AND DEPLOYMENT TRADE-OFFS
DOI:
https://doi.org/10.71146/kjmr900Keywords:
Spam detection, machine learning, deep learning, feature importance, classification, real-world trade-offsAbstract
The problem of spam detection has been a burning issue in the digital communication system nowadays with the growing amount and complexity of unwanted messages. This paper will provide a comparative analysis of the traditional machine learning, deep learning, and transformer-based language models in spam detection, and feature importance, as well as trade-offs in real-world deployment. The review analyzes the trends of performance that are reported in the literature, also outlines the importance of feature engineering and automated representation learning and mentions the practical issues such as computational cost, interpretability, robustness and adaptability. The results indicate that more sophisticated pre-trained models tend to be better predictors, whereas the lightweight traditional models are still appealing in resource-limited contexts.
Downloads
References
[1] I. AbdulNabi and Q. Yaseen. Spam email detection using deep learning techniques. Procedia Computer Science, 184(2):853–858, 2021.
[2] M. Adnan, M. O. Imam, M. F. Javed, and I. Murtza. Improving spam email classification accuracy using ensemble techniques: a stacking approach. International Journal of Information Security, 2023.
[3] Ahmed Abbood Ali and Alharith A. Abdullah. Email spam detection: A novel hybrid approach using machine and deep learning techniques. International Journal of Intelligent Engineering and Systems, 18(7), 2025.
[4] I Androutsopoulos, G Paliouras, V Karkaletsis, G Sakkis, C Spyropoulos, and P Stamatopoulos. Learning to filter spam e-mail: A comparison of maive bayesian and a memory-based approach. In Proceedings, pages 1–13, 2000.
[5] A. Barushka and P. Hajek. Spam detection on social networks using cost-sensitive feature selection and ensemble-based regularized deep neural networks. Neural Computing and Applications, 32(9):4239–4257, 2020.
[6] A. Barushka and P. Hajek. Spam detection on social networks using cost-sensitive feature selection and ensemble-based regularized deep neural networks. Neural Computing and Applications, 32(9):4239–4257, 2020.
[7] C. Beaman and H. Isah. Anomaly detection in emails using machine learning and header information. arXiv preprint arXiv:2404.09101, 2024.
[8] S. Beiranvand, M.B. Dowlatshahi, and A. Hashemi. A review on cost-based feature se-lection algorithms in the various applications of machine learning. Journal of Mahani Mathematical Research, 15(2):1–44, 2025.
[9] P. Bharath, T. Varadharaj, and S. K. Rigan raj. Comparative study of machine learning algorithms for spam email deduction. In Conference Proceeding ICNKAI-2K25, 2025.
[10] Gomez J C, E Boiy, and M.-F Moens. Highly discriminative statistical features for email classification. Knowledge and Information Systems, 31(1):23–53, 2012.
[11] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.
[12] H. Chen et al. Semi-supervised clue fusion for spammer detection in sina Weibo. Information Fusion, 44:22–32, 2018.
[13] Y. Guo, Z. Mustafaoglu, and D. Koundal. Spam detection using bidirectional transformers and machine learning classifier algorithms. Journal of Computational and Cognitive Engineering, 2(1):5–9, 2023.
[14] C.-W. Huang, C.-K. Chou, and M.-S. Chen. A salient ensemble of trees using cascaded linear classifiers with feature-cost constraints. In Proceedings of the 2018 SIAM International Conference on Data Mining, pages 486–494, 2018.
[15] N. Hussain, H. Turab Mirza, I. Hussain, F. Iqbal, and I. Memon. Spam review detection using the linguistic and spammer behavioral methods. IEEE Access, 8:53801–53816, 2020.
[16] A. Iqbal and M. Younas. An intelligent spam detection framework using fusion of spammer behavior and linguistic. PLoS ONE, 20(2):e0313628, 2025.
[17] H Iswanto, E Seniwati, Y Astuti, and D Maulina. Comparison of algorithms on machine learning for spam email classification. International Journal of Information System & Technology, 5(4):446–455, 2021.
[18] S. Kaddoura and G. Chandrasekaran. A systematic literature review on spam content detection and classification. PeerJ Computer Science, 8:e830, 2022.
[19] A. Karim, S. Azam, B. Shanmugam, K. Kannoorpatti, and M. Alazab. A comprehensive survey for intelligent spam email detection. IEEE Access, 7:168261–168295, 2019.
[20] A. A. B. S. J. Y. K. M. Y. Khan, M. A. A. B. Anindya, K. F. A. S. J. B. Al-Masum, and
K. M. A. F. A. Al-Nayeem. A benchmark study of machine learning models for online fake news detection. arXiv preprint arXiv:2103.15582, 2021.
[21] B. Kuchipudi, R. T. Nannapaneni, and Q. Liao. Adversarial machine learning for spam filters. In IWCC ’20: 9th International Workshop on Cyber Crime, 2020.
[22] P. Kulkarni, J. R. Saini, and H. Acharya. Effect of header-based features on accuracy of classifiers for spam email classification. The Science and Information (SAI) Organization, 11(3), 2020.
[23] C. Laorden, X. Ugarte-Pedrero, I. Santos, B. Sanz, J. Nieves, and P. G. Bringas. Study on the effectiveness of anomaly detection for spam filtering. Information Sciences, 277:421–444, 2014.
[24] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019.
[25] B. Long, E. Liu, R. Qiu, and Y. Duan. Explainable ai – the latest advancements and new trends. arXiv preprint arXiv:2308.11894, 2023.
[26] G. Mujtaba, L. Shuib, and R. Gunalan. Email classification research trends: Review and open issues. IEEE Access, 5, 2017.
[27] G. Nasreen, M. M. Khan, M. Younus, B. Zafar, and M. K. Hanif. Email spam detection by deep learning models using novel feature selection technique and bert. Egyptian Informatics Journal, 26:100473, 2024.
[28] H. Padhiyar and P. Rekh. An improved expectation maximization based semi-supervised email classification using naive bayes and k-nearest neighbor. Int. J. Comput. Appl., 101(6):7–11, 2014.
[29] J. Pennington, R. Socher, and C. D. Manning. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, 2014.
[30] M. N. Raihen, S. Rana, M. A. Kadir, and S. Akter. Efficient email spam detection using machine learning techniques: A comparative analysis of classification models. International Journal of Intelligent Computing and Information Sciences, 24(4):1–15, 2024.
[31] M. Salman, M. Ikram, and M. A. Kaafar. Investigating evasive techniques in SMS spam filtering: A comparative analysis of machine learning models. IEEE Access, 12:24306–24321, 2024.
[32] Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108, 2019.
[33] D Sculley and Wachman G M. Relaxed online svms for spam filtering. In Proceedings of the 30th annual international ACM SIGIR conference on research and development in information retrieval, pages 415–422, 2007.
[34] A. Sheneamer. Comparison of deep and traditional learning methods for email spam filtering. The Science and Information (SAI) Organization, 12(1), 2021.
[35] J.-J. Sheu, K.-T. Chu, N.-F. Li, and C.-C. Lee. An efficient incremental learning mechanism for tracking concept drift in spam filtering. Plos ONE, 12(2), 2017.
[36] M. C. Singh, P. Sumanth, S. B. Sathyanarayana, and G. Rithika. Phishing email detection using deep learning algorithms. International Journal of Health Sciences, 6(S3):8130–8139, 2022.
[37] J. S. Whissell and C. L. A. Clarke. Clustering for semi-supervised spam filtering. In Proceedings of the 8th Annual Collaboration, Electronic messaging, Anti-Abuse and Spam Conference, CEAS ’11, pages 125–134, 2011.
[38] L. Zhang, J. Zhu, and T. Yao. An evaluation of statistical spam filtering techniques. ACM Transactions on Asian Language Information Processing, 3(4):243–269, 2004.
[39] Y. Zhang, R. Jin, and Z. Zhou. Understanding bag-of-words model: A statistical frame-work. Int. J. Mach. Learn. Cybern., 1(1–4):43–52, 2010.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Aftab Ahmed, Dr. Samina Rajper, Bheem Sen Neel, Sarmad Khan (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
KJMR publishes all articles as open access under CC BY 4.0, allowing anyone to share and adapt the work, even commercially, with proper credit, a license link, and clear notice of changes, without implying endorsement. Authors retain copyright while granting the journal non-exclusive publishing and archiving rights and may self-archive without embargo. Third-party material requires proper permission, and the journal ensures long-term free access through its website and archiving partners.
How to Cite
