International Journal of Advanced Research in Computer and Communication Engineering

Abstract: Social media has become an essential part of modern communication, allowing people to connect, share, and express themselves. However, the growing presence of fake accounts on platforms like Instagram has become a serious issue, leading to the spread of misinformation, scams, and privacy risks. This project aims to detect fake Instagram profiles using machine learning techniques. Three algorithms—Support Vector Machine (SVM), Random Forest, and Decision Tree—are used to classify accounts as real or fake. The dataset includes user activity details, engagement patterns, and content-based features. The models are trained and compared based on their accuracy and efficiency. The results show that machine learning methods can effectively identify fake profiles and improve safety and trust on social media. Future work can involve integrating deep learning models and extending the system to other social platforms.

Keywords: Fake Accounts, Machine Learning, Instagram, SVM, Random Forest, Decision Tree, Social Media Security, User Behavior.

Downloads: | DOI: 10.17148/IJARCCE.2025.141159