Fake Account Detection on Instagram using Machine Learning

Abstract

In the present generation, online social networks (OSNs) have become increasingly popular, people’s social lives have become more associated with these sites. They use OSNs to keep in touch with each other’s, share news, organize events, and even run their own e-business. The rapid growth of OSNs and the massive amount of personal data of its subscribers have attracted attackers, and imposters to steal personal data, share false news, and spread malicious activities. Recognizing the urgency of addressing these threats, researchers have embarked on a quest to develop effective strategies for detecting and thwarting abnormal activities and fake accounts within OSNs. This paper proposes a novel approach, ADB-CB, aimed at bolstering the detection of fake Instagram accounts. By integrating advanced feature selection and dimension reduction techniques, coupled with the utilization of three distinct machine learning algorithms - Adaboost, Catboost and Extra tree classifier. We aim to enhance the accuracy and reliability of identifying fraudulent accounts.