A Survey of Spam Bots Detection in Online Social Networks

Abstract

Online Social networks (OSN) have become an integral part of people's lives. People from all over the world interact instantly between each other by sharing pictures and content. They can also express their opinion about politics, sport, and be part of influencing users in OSN. So, with the large growth of the number of users of OSN, it has become a target for the vicious people that post spam contents and messages. The malicious social bots (MSB) are one of the biggest threats that menace the social networks security and several studies have been conducted to detect them. In this work we focus on spam bots and reviewed all the existing bot detection techniques based on different features extracted from users' profiles and interactions. The paper analyzed and compared the proposed techniques between 2014 and 2021 to get the most relevant features that improve the spam bot detection and the most efficient Machine learning ML and Deep learning DL techniques from OSN. An investigation on existing datasets is proposed, some limitations of the studied approaches are outlined and future directions for social bot techniques detection improvement are proposed.