International Peer-Reviewed Journal•Open Access•ISSN 2456-8880
irejournals@gmail.com•+91-7433024337

Home / Current Issue / Paper 1722448

1722448 Vol 10 · Issue 2 Download Paper

Development of an Email Phishing Detection System Using TF–IDF Feature Extraction and Machine Learning Algorithms

Etus C. (PhD.) Ewunonu T. C. (PhD.) Chuks-Ugochukwu C. M. (PhD.) Esomonu N. F. (PhD.) Benson-Emenike M. E. (PhD.)

Subject area: Science,Engineering and Technology  ·  Area of research: Cybersecurity, Information Technology

DOI: 10.64388/IREV10I2-1722448

Abstract

The rapid expansion of digital communication has established email as a primary medium for information exchange among individuals, businesses, and organisations. This widespread reliance has contributed to a marked increase in phishing attacks, in which cybercriminals impersonate legitimate entities to obtain sensitive information, including login credentials, financial data, and personal details. Traditional phishing detection methods, including rule-based filters and blacklist mechanisms, have proven increasingly insufficient against sophisticated and evolving phishing strategies. As a result, there is a critical need for intelligent and adaptive detection systems capable of accurately identifying phishing emails. This study presents the development of an intelligent Email Phishing Detection System utilising supervised machine learning algorithms to enhance email security and protect users from phishing threats. A publicly available dataset containing both phishing and legitimate email messages was employed for model training and evaluation. The dataset underwent preprocessing steps including text cleaning, tokenisation, stop-word removal, and feature extraction using the Term Frequency–Inverse Document Frequency (TF–IDF) technique. Five supervised machine learning algorithms—Logistic Regression, Naïve Bayes, Decision Tree, Random Forest, and Support Vector Machine (SVM)—were trained and evaluated using standard performance metrics: accuracy, precision, recall, and F1-score. Experimental results indicated that the Support Vector Machine (SVM) outperformed the other classification models, achieving an accuracy of 99.1%, precision of 99.0%, recall of 99.1%, and an F1-score of 99.0%. Due to its superior performance, the SVM model was selected for deployment in the developed system. The proposed phishing detection system was implemented as a desktop application using Python's Tkinter graphical user interface (GUI), allowing users to input email content and receive real-time predictions regarding the legitimacy of emails. The findings demonstrate that machine learning techniques, particularly the Support Vector Machine algorithm, offer a highly accurate, reliable, and efficient approach to phishing email detection. Integrating the trained SVM model into a user-friendly desktop application provides a practical, lightweight, and scalable solution that enhances email security, reduces false detections, and assists users in more effectively identifying phishing attempts.

Keywords

email phishing, machine learning, support vector machine, cybersecurity, detection system.

References

[1] Ahmed, M., & Khan, R. (2022). Transformer-based multilingual email classifier for phishing

[2] detection. International Journal of Cybersecurity Research, 8(3), 114–128. https://doi.org/10.1016/ijcsr.2022.08.003

[3] Ahmed, M., Rehman, A., & Hussain, S. (2024). Detecting phishing in encrypted traffic using Long

[4] Short-Term Memory (LSTM) models. Journal of Network Security and Applications, 12(1), 45–59.

[5] Alkhalil, Z., Hewage, C., Nawaf, L., & Khan, I. (2021). Phishing attacks: A recent comprehensive

[6] study and a new anatomy. Frontiers in Computer Science, 3, 563060. https://doi.org/10.3389/fcomp.2021.563060

[7] Azmat Ullah, A., Javed, A., & Malik, S. (2024). Enhancing phishing detection leveraging deep

[8] learning techniques. IEEE Access, 12, 30412–30425.

[9] Chen, Y., Li, P., & Zhou, T. (2023). Phishing detection on e-commerce platforms using XGBoost.

[10] Journal of Information Security and Applications, 75, 103463. https://doi.org/10.1016/j.jisa.2023.103463

[11] Guo, W., Zhang, L., & Chen, Z. (2025). Efficient phishing URL detection using graph-based

[12] machine learning and loopy belief propagation. Computers & Security, 140, 103658.

[13] Gupta, P., & Rao, D. (2023). Adversarial robust phishing detection using generative adversarial

[14] networks (GANs). Computers & Security, 119, 102781.

[15] Mohamad Asraf Daniel, M. A., Rahman, N., & Zainal, N. (2025). Optimising phishing detection:

[16] A comparative analysis of machine learning methods with feature selection. Journal of Cyber Intelligence, 9(2), 99–113.

[17] Muhammad, F., Ahmed, I., & Noor, A. (2025). Web Phishing Net (WPN): A scalable machine

[18] learning approach for real-time phishing campaign detection. Expert Systems with Applications, 238, 121948.

[19] Patel, S., Mehta, R., & Chauhan, D. (2021). Lightweight phishing detection for mobile devices

[20] using decision trees. Journal of Mobile Computing and Network Security, 9(1), 20–29.

[21] Prabakaran, S., Subramanian, V., & Arumugam, K. (2023). Enhanced deep learning-based

[22] phishing detection using variational autoencoders. Neural Computing and Applications, 35(14), 10412–10426.

[23] Tan, W., & Lim, C. (2022). Reducing false negatives in phishing detection using hybrid random

[24] forest and logistic regression models. Journal of Information Security, 10(3), 112–124.

[25] Wang, Y., Liu, Q., & Zhang, Y. (2021). CNN-based detection of phishing URLs using lexical and

[26] visual features. Expert Systems with Applications, 168, 114272.

[27] https://doi.org/10.1016/j.eswa.2020.114272

[28] Zhang, L., & Li, J. (2020). Phishing email detection using BERT-based natural language

[29] processing models. IEEE Transactions on Information Forensics and Security, 15, 3652–3663.

[30] Zhou, X., & Chen, K. (2024). Blockchain-integrated decentralised framework for phishing

[31] detection systems. Journal of Network and Computer Applications, 210, 103510. https://doi.org/10.1016/j.jnca.2024.103510

How to cite this paper

Etus C. (PhD.), Ewunonu T. C. (PhD.), Chuks-Ugochukwu C. M. (PhD.), Esomonu N. F. (PhD.), Benson-Emenike M. E. (PhD.) "Development of an Email Phishing Detection System Using TF–IDF Feature Extraction and Machine Learning Algorithms" Iconic Research And Engineering Journals Volume 10 Issue 2 2026 Page 2430-2445 https://doi.org/10.64388/IREV10I2-1722448
Etus C. (PhD.), Ewunonu T. C. (PhD.), Chuks-Ugochukwu C. M. (PhD.), Esomonu N. F. (PhD.), Benson-Emenike M. E. (PhD.) "Development of an Email Phishing Detection System Using TF–IDF Feature Extraction and Machine Learning Algorithms" Iconic Research And Engineering Journals, vol. 10, no. 2, Aug. 2026, doi: https://doi.org/10.64388/IREV10I2-1722448
Etus C. (PhD.), Ewunonu T. C. (PhD.), Chuks-Ugochukwu C. M. (PhD.), Esomonu N. F. (PhD.), Benson-Emenike M. E. (PhD.) (2026). Development of an Email Phishing Detection System Using TF–IDF Feature Extraction and Machine Learning Algorithms. Iconic Research And Engineering Journals, 10(2). doi: https://doi.org/10.64388/IREV10I2-1722448
Etus C. (PhD.), Ewunonu T. C. (PhD.), Chuks-Ugochukwu C. M. (PhD.), Esomonu N. F. (PhD.), Benson-Emenike M. E. (PhD.) "Development of an Email Phishing Detection System Using TF–IDF Feature Extraction and Machine Learning Algorithms" Iconic Research And Engineering Journals, vol. 10, no. 2, Aug. 2026. Crossref, https://doi.org/10.64388/IREV10I2-1722448
@article{1722448,
      author = {Etus C. (PhD.), Ewunonu T. C. (PhD.), Chuks-Ugochukwu C. M. (PhD.), Esomonu N. F. (PhD.), Benson-Emenike M. E. (PhD.)},
      title = {Development of an Email Phishing Detection System Using TF–IDF Feature Extraction and Machine Learning Algorithms},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {2},
      pages = {2430-2445},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722448.pdf},
      abstract = {The rapid expansion of digital communication has established email as a primary medium for information exchange among individuals, businesses, and organisations. This widespread reliance has contributed to a marked increase in phishing attacks, in which cybercriminals impersonate legitimate entities to obtain sensitive information, including login credentials, financial data, and personal details. Traditional phishing detection methods, including rule-based filters and blacklist mechanisms, have proven increasingly insufficient against sophisticated and evolving phishing strategies. As a result, there is a critical need for intelligent and adaptive detection systems capable of accurately identifying phishing emails. This study presents the development of an intelligent Email Phishing Detection System utilising supervised machine learning algorithms to enhance email security and protect users from phishing threats. A publicly available dataset containing both phishing and legitimate email messages was employed for model training and evaluation. The dataset underwent preprocessing steps including text cleaning, tokenisation, stop-word removal, and feature extraction using the Term Frequency–Inverse Document Frequency (TF–IDF) technique. Five supervised machine learning algorithms—Logistic Regression, Naïve Bayes, Decision Tree, Random Forest, and Support Vector Machine (SVM)—were trained and evaluated using standard performance metrics: accuracy, precision, recall, and F1-score. Experimental results indicated that the Support Vector Machine (SVM) outperformed the other classification models, achieving an accuracy of 99.1%, precision of 99.0%, recall of 99.1%, and an F1-score of 99.0%. Due to its superior performance, the SVM model was selected for deployment in the developed system. The proposed phishing detection system was implemented as a desktop application using Python's Tkinter graphical user interface (GUI), allowing users to input email content and receive real-time predictions regarding the legitimacy of emails. The findings demonstrate that machine learning techniques, particularly the Support Vector Machine algorithm, offer a highly accurate, reliable, and efficient approach to phishing email detection. Integrating the trained SVM model into a user-friendly desktop application provides a practical, lightweight, and scalable solution that enhances email security, reduces false detections, and assists users in more effectively identifying phishing attempts.},
      keywords = {email phishing, machine learning, support vector machine, cybersecurity, detection system. },
      month = {August},
      doi = {https://doi.org/10.64388/IREV10I2-1722448}
  }