Anonymous and Lucky Troll Club have used crowd sourcing to identify and expose

Anonymous and lucky troll club have used crowd

This preview shows page 13 - 15 out of 20 pages.

Anonymous and Lucky Troll Club have used crowd sourcing to identify and expose ISIS OEC members on Twitter [ 16 18 ]. These attempts to limit ISIS’ use of social media platforms has resulted in a predator-prey-like system where the ISIS OEC on Twitter has begun show systematic attempts to make the network anonymous and resilient. Our work makes three major contributions to the literature. First, we present Iterative Vertex Clustering and Classification (IVCC), a novel approach to detect and extract knowledge from OECs. Our approach utilizes community optimization methods in conjunction with multiplex vertex classification (MVC) , a classification method used on heterogeneous graphs that leverages the rich data structures common to many OSNs like user meta-data, mentioning, following, and hash tag use. Capitalizing on this rich structure enables us to outperform existing methods with respect to recall and precision which will be shown in Section 4. After considering the merits of our approach, we then turn to the second major contribution of this work, an illustrative case study of the ISIS OEC on Twitter. By searching known members’ following ties and partitioning the resultant network, we
Image of page 13
identify a community of over 22,000 Twitter users whose online behavior contributes to the online proliferation of ISIS propaganda. We leverage clustering and Twitter suspensions to infer positive case instances with our classifier which is able to partition our training set with 96% accuracy. This offers significant improvement over existing methods, and we claim this makes our output uniquely valid for the study of online radicalization. Finally, we discuss an ethical framework for the implementation of methods similar to IVCC. We highlight the framework presented in [ 19 ] of: methods, context, and target, and we draw distinctions in context between diplomatic and intelligence applications of social media mining. We structure this article as follows: In Section 1 we discuss related work and highlight the limitations of common community detection methodologies with respect to OEC detection. Section 2 provides a detailed overview of our proposed community detection methodology, followed by an illustrative case study of the ISIS OEC on Twitter in Section 3. Section 4 provides a detailed discussion of the relative performance of IVCC, and Section 5 provides a case study of the ISIS supporting OEC on Twitter and illustrative knowledge extractions useful for counter-messaging or intelligence purposes. We then discuss the societal implications and limitations associated with the potential uses of our methods in Section 6, and propose future research in Section 7. 1 Background Krebs [ 20 , 21 ] was the first to cast large-scale attention on network science-based counter-terrorism analysis with his application of network science techniques to gain insight into the September 11, 2001 World Trade Center Bombings. Although similar methods were presented years earlier [ 22 ], the timeliness of Krebs’ work caught the
Image of page 14
Image of page 15

You've reached the end of your free preview.

Want to read all 20 pages?

  • Fall '17

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Ask Expert Tutors You can ask You can ask ( soon) You can ask (will expire )
Answers in as fast as 15 minutes