Development of an Efficient Machine learning-based Email spam Detection System
1Akawuku, I. Godspower , 2Adejumo, Samuel Olujimi, 3Alade, Samuel Mayowa, 4Olatunde, Ayodeji Akano, 5David and Mulumeoderhwa Bahati
1Department of Software Engineering, Nnamdi Azikiwe University, Awka, Nigeria
2Departments of Cybersecurity, Nnamdi Azikiwe University, Awka, Nigeria
3Department of Computer Science, Nnamdi Azikiwe University, Awka, Nigeria
4Department of Computer Sciences, Abiola Ajimobi Technical University, Ibadan, Nigeria
5Department of Computer Science, Olivia University, Bujumbura, Burundi.
Email: gi.akawuku@unizik.edu.ng
ABSTRACT
Email spam remains a persistent threat to digital communication, with estimates indicating that over 50% of daily global email traffic is spam. To address this issue, this paper presents the development of an accurate and efficient email spam detection system using machine learning techniques, guided by the Object-Oriented Analysis and Design (OOAD) methodology. The integration of OOAD allowed for a systematic, modular, and scalable approach to system design, facilitating clear separation of concerns, reusability, and maintainability. The system architecture was modeled using Unified Modeling Language (UML) diagrams to define key components such as data preprocessing, feature extraction, model training, classification, and user interaction. The spam detection engine was developed using supervised machine learning algorithms including Naive Bayes, Support Vector Machines (SVM), and Random Forest, trained on a large, labeled dataset of spam and non-spam emails. Feature engineering incorporated natural language processing (NLP) techniques to capture the textual patterns characteristic of spam content. Performance evaluation demonstrated that the system achieved high accuracy (over 98%) and strong precision-recall balance, making it suitable for real-time applications. By combining OOAD methodology with robust machine learning models, this study offers a structured and efficient solution to email spam detection. The resulting system is not only accurate and scalable but also maintainable and extensible for future enhancements. This work underscores the importance of combining sound software engineering principles with intelligent algorithms to combat the evolving landscape of email-based threats.
Keywords: Machine learning-based, Email spam, Detection System, Object-Oriented Analysis and Design (OOAD) methodology.
CITE AS: Akawuku I. Godspower , Adejumo Samuel Olujimi, Alade Samuel Mayowa, Olatunde Ayodeji Akano David and Mulumeoderhwa Bahati (2025) Development of an Efficient Machine learning-based Email spam Detection System. NEWPORT INTERNATIONAL JOURNAL OF ENGINEERING AND PHYSICAL SCIENCES, Volume 5 Issue 2 Page 1-10. https://doi.org/10.59298/NIJEP/2025/5211000