DETECTING MALICIOUS TWITTER BOTS USING MACHINE LEARNING

Abstract

In today's world, Twitter is used often & has taken on significance in lives about many individuals, including businessmen, media, politicians, & others. One about most popular social networking sites, Twitter enables users towards share their opinions on a range about subjects, including politics, sports, financial market, entertainment, & more. It is one about fastest methods about information transfer. It significantly influences how individuals think. There are more people on Twitter who mask their identities for malicious reasons. Because it poses a risk towards other users, it is important towards recognise Twitter bots. Therefore, it is crucial that tweets are posted through real people & not Twitter bots. A twitter bot posts spam-related topics. Thus, identifying bots aids in identifying spammessages. Twitter account attributes are used as Features in machine learning algorithms towards categorise users as real or false. In this study, we employed Decision Tree, Random Forest, &Multinomial Naive Bayes as three machine learning methods towards determine if an account was authentic or not. algorithms' accuracy & classificationperformance are compared. Multinomial Naive Bayesmethod has an accuracy about 89%, Random Forest algorithm about 90%, & Decision Tree algorithm about 93%. As a result, it can be seen that Decision tree performs among greater accuracy than Random Forest & Multinomial Nave Bayes.