Spammer Detection in Social Networks using ML and NLP

Spammers have turned some of the most popular places for people to communicate with each other into a distribution platform for shoddy and perhaps harmful information. Many individuals, all around the world, make use of online services for connecting with others in real time. To provide just one example, Facebook has grown to become one of the most widely used platforms ever, allowing an unacceptably large amount of spam to be transmitted from the site. There has been an increase in the potential for disseminating dangerous information to customers via the use of fictitious identities. As a result, the identification of spammers and fake Twitter clients has recently appeared as an unmistakable research problem in modern online interpersonal organizations (OSNs). On the web-based media platform Twitter, spammers may be identified using a variety of techniques. A scientific classification of Twitter spam location strategies is also presented, which divides the strategies into four categories based on their ability to distinguish I counterfeit material, (ii) spam dependent on URL, (iii) spam in hot subjects, and (iv) fake clients on the person-to-person communication site. Researchers seeking for the aspects of continuous advancements in Facebook spam detection may benefit from this investigation.