Time-to-Event Modeling for Predicting Hacker IRC Community Participant Trajectory

As computing and communication technologies become ubiquitous throughout society, researchers and practitioners have become motivated to advance current cybersecurity capabilities. In particular, research on the human element behind cybercrime would offer new knowledge on securing cyberspace against those with malicious intent. Past work documents the existence of many hacker communities with participants sharing various cybercriminal assets and knowledge. However, participants vary in expertise, with some possessing only passing curiosity while others are capable cybercriminals. Here we develop a time-to-event based approach for assessing the relationship between various participation behaviors and participation length among hacker Internet Relay Chat (IRC) community participants. Using both the Kaplan-Meier model and Cox's model, we are able to develop predictions on individuals' participation trajectorybased on a series of message content and social network features. Results indicate that participation volume, discussion of pertinent topics, and social interconnectedness are all important at varying levels for identifying participants within hacker communities that have potential to become adept cybercriminals.