Social media analytics is a critical research area spawned by the increasing availability of rich and abundant online user-generated content. So far, social media analytics has had a profound impact on organizational decision making in many aspects, including product and service design, market segmentation, customer relationship management, and more. However, the cybersecurity sector is behind other sectors in benefiting from the business intelligence offered by social media analytics. Given the role of hacker communities in cybercrimes and the prevalence of hacker communities, there is an urgent need for developing hacker social media analytics capable of gathering cyber threat intelligence from hacker communities for exchanging hacking knowledge and tools.
My dissertation addressed two broad research questions: (1) How do we help organizations gain cyber threat intelligence through social media analytics on hacker communities? And (2) how do we advance social media analytics research by developing innovative algorithms and models for hacker communities? Using cyber threat intelligence as a guiding principle, emphasis is placed on the two major components in hacker communities: threat actors and their cybercriminal assets. To these ends, the dissertation is arranged in two parts. The first part of the dissertation focuses on gathering cyber threat intelligence on threat actors. In the first essay, I identify and profile two types of key sellers in hacker communities: malware sellers and stolen data sellers, both of which are responsible for data breach incidents. In the second essay, I develop a method for recovering social interaction networks, which can be further used for detecting major hacker groups, and identifying their specialties and key members. The second part of the dissertation seeks to develop cyber threat intelligence on cybercriminal assets. In the third essay, a novel supervised topic model is proposed to further address the language complexities in hacker communities. In the fourth essay, I propose the development of an innovative emerging topic detection model. Models, frameworks, and design principles developed in this dissertation not only advance social media analytics research, but also broadly contribute to IS security application and design science research.
| Identifer | oai:union.ndltd.org:arizona.edu/oai:arizona.openrepository.com:10150/625640 |
| Date | January 2017 |
| Creators | Li, Weifeng, Li, Weifeng |
| Contributors | Chen, Hsinchun, Chen, Hsinchun, Nunamaker, Jay F., Jr., Brown, Susan |
| Publisher | The University of Arizona. |
| Source Sets | University of Arizona |
| Language | en_US |
| Detected Language | English |
| Type | text, Electronic Dissertation |
| Rights | Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author. |
Page generated in 0.002 seconds