Classifying social media bots as malicious or benign using semi-supervised machine learning

Abstract

Users of online social network (OSN) platforms, e.g. Twitter, are not always humans, and social bots (referred to as bots) are highly prevalent. State-of-the-art research demonstrates that bots can be broadly categorized as either malicious or benign. From a cybersecurity perspective, the behaviors of malicious and benign bots differ. Malicious bots are often controlled by a botmaster who monitors their activities and can perform social engineering and web scraping attacks to collect user information. Consequently, it is imperative to classify bots as either malicious or benign on the basis of features found on OSNs. Most scholars have focused on identifying features that assist in distinguishing between humans and malicious bots; the research on differentiating malicious and benign bots is inadequate. In this study, we focus on identifying meaningful features indicative of anomalous behavior between benign and malicious bots. The effectiveness of our approach is demonstrated by evaluating various semi-supervised machine learning models on Twitter datasets. Among them, a semi-supervised support vector machine achieved the best results in classifying malicious and benign bots.