Fake Profile Detection on Social Media Using Machine Learning

Sakshi Tapkir

Abstract: Social media platforms are growing fast. This growth has led to fake user profiles. These profiles are used for stealing identities and spreading information. It is hard for people to find these accounts manually because there are users and the behavior of these accounts is always changing. This paper talks about a system that uses machine learning to find social media profiles. The system looks at things like the number of followers the number of accounts the profile follows, how often the profile posts, how old the account is, if the profile has a picture and if the account is verified. The system uses these things to train and test three machine learning algorithms: Logistic Regression, Support Vector Machine and Random Forest. When we tested the system, we found that the Random Forest algorithm was the best at finding profiles. It was correct 95.8% of the time. The system is a way to make social media more secure and trustworthy.

Keywords: Fake profile detection, social media security, machine learning, Random Forest, Support Vector Machine, Logistic Regression, feature extraction, classification