Investigating Cybersecurity News Articles by Applying Topic Modeling Method

Abstract

Machine Learning (ML) and specifically Natural Language Processing (NLP) are increasingly used as tools in the cybersecurity world. These NLP tools bring new capabilities that support both defenders and attackers in their activities, whether it is risk scenarios such as events and threats or security operations. Ours is a unique case study as we are investigating cybersecurity news on a national and global level. This large study covered six countries and 18 major newspapers and analyzed thousands of cybersecurity articles using the Nonnegative Matrix Factorization (NMF) topic modeling method. News making and policymaking complement each other in forming national identities. This research aims to provide the foundation for the field of Cybersecurity in this direction. Our results showed the US dominance and its significance for other countries. This research also highlighted that much of the US media’s cybersecurity reporting focuses on domestic issues, unlike other nations.