1 / 8

Five months with the Devils: Identifying Content Polluters in Social Streams

Five months with the Devils: Identifying Content Polluters in Social Streams. By Radina Kalpakova. Why would it matter?. Problem gaining popularity but not yet well understood Can cause severe implications on society – vandalism, protests, rebellions 2.0 security for 2.0 websites

blaine
Download Presentation

Five months with the Devils: Identifying Content Polluters in Social Streams

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Five months with the Devils: Identifying Content Polluters in Social Streams By RadinaKalpakova

  2. Why would it matter? • Problem gaining popularity but not yet well understood • Can cause severe implications on society – vandalism, protests,rebellions • 2.0 security for 2.0 websites • Legal issues involved – Freedom of speech • Attempt of preserving high quality content on the web.

  3. How can we identify content polluters in Social Streams Accurately? • What drives polluters’ behavior? Why are they doing it? What are their motives? • What distinguishes polluters from legitimate users? • How can we detect them?

  4. How would we solve it? • Analyze and identify differences between the behavior of polluters and legitimate users • Create a set of polluters profiles based on chosen features – relationship with other users, posting frequency and content, interaction with other users, web links posted, reputation, etc. • Set social honeypots to attract potential polluters • Experiment with various classification approaches with the aim to find the optimum features that maximize the classification results (social graph modeling, feature selection etc. )

  5. Background literature • Kyumin Lee, Brian David Eoff, James Caverlee, “Seven months with the Devils: A long-term study on Content Polluters on Twitter”, 5th International AAAI Conference on Weblogs and Social Media (ICWSM). Barcelona, July, 2011. • Alex Hai Want, “Don’t follow me: spam detection in Twitter”, College of Information Sciences and Technology, The Pennsylvania State University • Marco Papic and Sean Noonan, “Social Media as tool for protest”, Feb 3, 2011.

  6. Who would I want to work with? • Like minded people • Strong coders • Good Writers

  7. References • http://www.b-fair.net/wp-content/themes/majalah/timthumb.php?src=http://www.b-fair.net/wp-content/uploads/2012/08/pollution.jpg&h=260&w=600&zc=1 – Last accessed on 17/10/2012 • http://images.businessweek.com/ss/07/11/1115_in_short/image/ball.jpg - Last accessed on 17/10/2012 • http://www.edupics.com/coloring-page-thinking-i11499.html - Last accessed on 17/10/2012

  8. Thank You

More Related