FAKE SOCIAL MEDIA ACCOUNTS DETECTION USING MACHINE LEARNING

Abstract

The rapid growth of social media platforms has resulted in an increase in fake accounts that are used for spam, identity theft, phishing, misinformation, and fraudulent activities. Detecting such accounts manually is difficult because of the large number of users and continuously changing account behaviour. This paper presents a Machine Learning-based Fake Social Media Accounts Detection system that automatically classifies social media accounts as real or fake using accountrelated features. The proposed system performs data preprocessing, visualization, feature encoding, and model training using Logistic Regression, Decision Tree, and Random Forest algorithms. After comparing the performance of these models, the bestperforming model is selected and deployed in a Flask web application. The application allows users to register, log in, provide account details, and receive instant predictions. The prediction history is stored using SQLite for future reference. The proposed system provides a simple, efficient, and user-friendly solution for detecting fake social media accounts and demonstrates how Machine Learning can support online security.