Intelligent Identification of Fake Accounts on Social Media

Abstract

The paper presents an original research of fake accounts on social media using an artificial neural network for their identification. Specifically designed and implemented application was used to identify specific features of fake accounts and study the principles and reasons of their generation. Considering the possible use cases and scenarios of its practical use including everyday social media surfing there was examined a possibility to implement a mobile application based on Java in the Android Studio programming environment. Based on the study of 500 real and 500 fake VKontakte accounts there was determined a number of conclusions on the original features of fake accounts. The provided research allowed extending the list of criteria for identifying fake accounts by an original set of patterns. The developed conclusions allow formulating the statements on what criteria can be used for further identification of fake accounts in practical applications.

Keywords

• social media analysis
• artificial intelligence
• fake accounts identification
• decision-making support