MACHINE LEARNING STRATEGIES FOR MALICIOUS TWITTER BOT DETECTION

Abstract

This study explores the application of machine learning techniques to detect malicious Twitter bots, which pose significant risks to information integrity and public discourse on social media platforms. By leveraging a combination of user behavior analysis, tweet content examination, and engagement metrics, we developed a robust model capable of distinguishing between authentic users and automated accounts exhibiting harmful behaviors. Our approach includes feature engineering, data preprocessing, and the implementation of various classification algorithms, evaluated through rigorous performance metrics. The results demonstrate the effectiveness of machine learning in identifying bots with high accuracy, providing insights into their operational patterns. This research contributes to the ongoing efforts to enhance the security and reliability of online communication environments.