Determining predisposition to insider threat activities by using text analysis
Insider threats are difficult to deal with because employees in any organization have a certain level of access to the company's secure network which bypasses the external security measures such as firewalls that have been put in place to protect the organization. The goal of this paper is to design and implement a predictive model which uses linguistic analysis as well as K-means to determine an employee's risk level computer-mediated communication specifically emails and related social networking. Computer-mediated communication (CMC) is a form of communication over virtual spaces where users cannot see each other's face. CMC includes email and communication over social networks, amongst others. This will be accomplished by determining whether or not employees meet certain personality criteria which establish how much of a risk they pose to their employers. In this study, various datasets are used including a real-world case study as a test bed for designed algorithm and tested results.
FTC 2016 - Proceedings of Future Technologies Conference
Digital Object Identifier (DOI)
Hongmei Chi, Scarllet, C., Prodanoff, Z. G., & Hubbard, D. (2016). Determining predisposition to insider threat activities by using text analysis. 2016 Future Technologies Conference (FTC), 985–990. https://doi.org/10.1109/FTC.2016.7821723