Detection of Fake Twitter Accounts Using Ensemble Learning Model

The prevalence of fake accounts on social media platforms poses significant threats to user safety and data integrity. The ability to detect such accounts before users interact with them is crucial in safeguarding the network against advanced attacks and cyber threats. With an increasing number of Internet users relying on social media for daily tasks, including cloud sharing, news reading, messaging, product reviews, and event discussions, the risk of encountering cybercriminals using fake accounts has amplified. In this research paper, we present an approach for detecting false identities in the Twitter platform. Our proposed system utilizes a range of categorization algorithms, including Naive Bayes and Decision Tree algorithms with ensemble learning models, to effectively identify fake social media profiles. By integrating these powerful algorithms, we achieve an impressive accuracy rate of 98.93% in distinguishing fake accounts from genuine ones. The contribution of this research lies in providing a robust and reliable solution to combat the proliferation of fake accounts on Twitter. By enabling the timely detection and elimination of fraudulent profiles, our approach strengthens the network's security and protects users from malicious entities, including trolls, internet fraudsters, deceptive advertising campaigns, and sexual predators.