Abstract. Software vulnerabilities constitute a major problem for today's world, which relies more than ever to technological achievements. The characterization of vulnerabilities' severity is an issue of major importance in order to address them and extensively study their impact on information systems. That is why scoring systems have been developed for the ranking of vulnerabilities' severity. However, the severity scores are based on technical information and are calculated by combining experts' assessments. The motivation for the study conducted in this paper was the question of whether the severity of vulnerabilities is directly related to their description. Hence, the associations of severity scores and individual characteristics with vulnerability descriptions' terms were studied using Text Mining, Principal Components and correlation analysis techniques, applied to all vulnerabilities registered in the National Vulnerability Database. The results are promising for the determination of severity by the use of the description since significant correlations were found.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.