Twitter Spam Detection and Traffic Classification

The rapid growth of the Internet and social media has led to an increase in the size of Internet traffic and the complexity of analyzing traffic behavior, especially in large-scale networks like social media platforms. Traditional rule-based methodologies are being replaced by automated approaches powered by machine learning, driven by the availability of large datasets that enable high-performance AI models. This book reviews recent research on cyber traffic analysis over social networks and the Internet, focusing on similarity, correlation, and collective indication concepts, and emphasizing the importance of security goals in classifying network hosts, applications, users, and tweets. To tackle these challenges, the paper introduces a new research methodology called data-driven cyber security (DDCS) and its application in analyzing social and Internet traffic. The DDCS methodology consists of three main components: cyber security data processing, cyber security feature engineering, and cyber security modeling.