Abstract

Cybercrime is often approached as a technical problem, but its global distribution reflects broader social, institutional, and governance conditions. This talk examines cybercrime as a socio-technical system through two complementary studies. First, using FireHOL IP blocklist data, I compare a Generalized Linear Model (GLM) with several non-linear machine learning approaches to identify the global drivers of cybercrime. The Random Forest Regressor achieves the strongest predictive performance, showing that cybercrime is shaped by complex, non-linear relationships that are not well captured by conventional linear approaches. Socio-economic and governance variables—including poverty rate, adult population, government effectiveness, and rule of law—emerge as especially important predictors, highlighting that cybercrime is not driven by technical infrastructure alone. Second, I examine how U.S. criminology and criminal justice doctoral programs are preparing scholars to study this increasingly complex domain. A review of 43 Ph.D. programs shows that only about half offer cybercrime-related coursework, with just six maintaining dedicated laboratories. Cybercrime is typically treated as an elective and often lacks technical or interdisciplinary depth. Taken together, these findings reveal a mismatch between the complexity of cybercrime and the current structure of doctoral training. The talk argues for a more integrated approach that connects computational methods, social science theory, and interdisciplinary training to better understand and respond to cybercrime.

Speaker Bio

Dr. Ling Wu is an Associate Professor in the Department of Criminology and Criminal Justice at the University of Alabama. Her research focuses on cybercrime, cyber victimization, and the social and structural dimensions of digital crime. Her work applies quantitative and computational approaches to examine how technological, social, and institutional factors shape cybercrime risks and patterns.