Machine Learning Techniques for Fake Account Detection in Social Networks
Authors: Abdul Muthalib Mohammed, MCA Student Dr. K. Santhi Sree, Professor Department of Information Technology, Jawaharlal Nehru Technological University Hyderabad, Telangana, India Email: abdulmuthallib18@gmail.com, drksanthisree@gmail.com
Journal: International Journal of Computer Techniques – Volume 12 Issue 4 Publication Date: July – August 2025 ISSN: 2394-2231 URL:https://ijctjournal.org/
Abstract
This paper explores the use of machine learning models to detect fake profiles in online social networks. Models including Random Forest, Naïve Bayes, SVM, KNN, and Logistic Regression were evaluated using accuracy, precision, recall, and F1-score. Random Forest achieved the highest accuracy of 97.5%, followed closely by Naïve Bayes at 97%. The study highlights the effectiveness of ensemble and probabilistic classifiers and suggests future research in deep learning and behavioral analysis for real-time detection.
Keywords
Fake Profile Detection, Social Networks, Machine Learning, Random Forest, Naïve Bayes, SVM, KNN, Logistic Regression, Cybersecurity, Online Identity Fraud
Conclusion
Among the evaluated models, Random Forest and Naïve Bayes emerged as the most effective for fake account detection. The study confirms the reliability of ensemble and probabilistic approaches in identifying malicious profiles. Future research should explore deep learning, real-time detection, and behavioral modeling to enhance adaptability and precision.
Post Comment