Enhanced Spam detection in SMS Communication Using Machine Learning and NLP Techniques
Sir Syed University Research Journal of Engineering & Technology · 28.06.2026 · 16 (1) · 41-51
DOI: 10.33317/ssurj.732 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sir Syed University Research Journal of Engineering & Technology, online erschienen am 28.06.2026. Verfasst von Rubina Shaheen und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Unwanted Spam communications spread over a variety of electronic means are harmful. Malicious communications delivered to numerous individuals on various channels without their consent can be dangerous as they commonly include links and unsolicited material that can result in financial fraud, phishing scams, and distinctiveness theft. Given the nature of cybersecurity concern, it is needed to resort to technical advancements for detection of spam messages. Machine learning has been effective for spam detection for the past several years, and deep learning has also shown strong performance. In this study, we evaluate five classifiers Logistic Regression (LR), Support Vector Machines (SVM), Gradient Boosting (GB), Random Forests (RF), and Multinomial Naïve Bayes (MNB) and their ensembles for spam message detection. We proposed usage of hard voting and soft voting classifier ensembles and analyzed their performance. The ensemble classifiers consistently showed improved performance particularly soft voting ensemble classifier. It surpassed individual models in terms of both accuracy and precision. We evaluated various configurations of the top performing individual classifiers and out of these our best configuration (soft-voting ensemble classifier consisting of RF, GB, and SVM), achieved 97.42% accuracy, outperforming the best individual classifier (with the accuracy of 97.10%). Thus, indicating a more robust and reliable approach for SMS spam detection. These findings emphasize the advantage of ensemble methods in enhancing SMS spam detection performance and mitigating the risks affiliated with spam communications.
Zitieren
APA
Shaheen, R., Akram, B. A., Ghauri, I. K., & Oad, A. (2026). Enhanced Spam detection in SMS Communication Using Machine Learning and NLP Techniques. Sir Syed University Research Journal of Engineering & Technology, 16(1), 41-51. https://doi.org/10.33317/ssurj.732
Vancouver
Shaheen R, Akram BA, Ghauri IK, Oad A. Enhanced Spam detection in SMS Communication Using Machine Learning and NLP Techniques. Sir Syed University Research Journal of Engineering & Technology. 2026;16(1):41-51. doi:10.33317/ssurj.732
BibTeX
@article{Shaheen2026,
author = {Shaheen, Rubina and Akram, Beenish Ayesha and Ghauri, Ifrah Khalid and Oad, Ammar},
title = {Enhanced Spam detection in SMS Communication Using Machine Learning and NLP Techniques},
journal = {Sir Syed University Research Journal of Engineering & Technology},
year = {2026},
volume = {16},
number = {1},
pages = {41--51},
doi = {10.33317/ssurj.732}
}
EUVIMED