INTELLIGENT FAKE PROFILE DETECTION IN SOCIAL NETWORKS USING MACHINE LEARNING AND NLP

Abstract

In recent years, social networking platforms have become an integral part of human life, enabling users to communicate, share information, and build communities. However, the rapid growth of these platforms has also led to an increase in fake profiles, which are often used for malicious activities such as spamming, identity theft, fraud, and spreading misinformation. Detecting such fake profiles has become a critical challenge in ensuring the security and reliability of online social networks. This project proposes a machine learning-based approach combined with Natural Language Processing (NLP) techniques to detect fake profiles effectively. The system uses structured profile data and textual information to classify user accounts as genuine or fake. Various pre-processing techniques such as data cleaning, feature extraction, and normalization are applied to improve model performance. Machine learning algorithms like Support Vector Machine (SVM), Naïve Bayes, Random Forest, and K-Nearest Neighbors (KNN) are used to train and test the dataset. The system evaluates model performance using accuracy metrics and visualizes results through charts. The proposed system demonstrates improved detection accuracy and provides a scalable solution for real-time applications.