Die Free or Live Hard? Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers

  • Chao Yang
  • Robert Chandler Harkreader
  • Guofei Gu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6961)


Due to the significance and indispensability of detecting and suspending Twitter spammers, many researchers along with the engineers in Twitter Corporation have devoted themselves to keeping Twitter as spam-free online communities. Meanwhile, Twitter spammers are also evolving to evade existing detection techniques. In this paper, we make an empirical analysis of the evasion tactics utilized by Twitter spammers, and then design several new and robust features to detect Twitter spammers. Finally, we formalize the robustness of 24 detection features that are commonly utilized in the literature as well as our proposed ones. Through our experiments, we show that our new designed features are effective to detect Twitter spammers, achieving a much higher detection rate than three state-of-the-art approaches [35,32,34] while keeping an even lower false positive rate.


Detection Feature Betweenness Centrality Twitter Account Evasion Tactic Spam Account 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    A new look at spam by the numbers, http://scitech.blogs.cnn.com/
  2. 2.
  3. 3.
  4. 4.
  5. 5.
    Botnet over Twitter, http://compsci.ca/blog/
  6. 6.
    Buy a follower, http://buyafollower.com/
  7. 7.
  8. 8.
  9. 9.
  10. 10.
  11. 11.
  12. 12.
  13. 13.
    The 2000 Following Limit Policy On Twitter, http://twittnotes.com/2009/03/2000-following-limit-on-twitter.html
  14. 14.
  15. 15.
  16. 16.
  17. 17.
  18. 18.
    Twitter API in Wikipedia, http://apiwiki.twitter.com/
  19. 19.
    Twitter phishing hack hits BBC, Guardian and cabinet minister, http://www.guardian.co.uk/technology/2010/feb/26/twitter-hack-spread-phishing
  20. 20.
    Twitter Public Timeline, http://twitter.com/public_timeline
  21. 21.
    Axelsson, S.: The base-rate fallacy and its implications for the difficulty of intrusion detection. In: Proceedings of the 6th ACM Conference on Computer and Communications Security, pp. 1–7 (1999)Google Scholar
  22. 22.
    Benevenuto, F., Magno, G., Rodrigues, T., Almeida, V.: Detecting Spammers on Twitter. In: Collaboration, Electronic messaging, Anti-Abuse and Spam Confference, CEAS (2010)Google Scholar
  23. 23.
    Benevenuto, F., Rodrigues, T., Almeida, V., Almeida, J., Gonalves, M.: Detecting Spammers and Content Promoters in Online Video Social Networks. In: ACM SIGIR Conference, SIGIR (2009)Google Scholar
  24. 24.
    Benevenuto, F., Rodrigues, T., Almeida, V., Almeida, J., Zhang, C., Ross, K.: Identifying Video Spammers in Online Social Networks. In: Int’l Workshop on Adversarial Information Retrieval on the Web, AirWeb 2008 (2008)Google Scholar
  25. 25.
    Cha, M., Haddadi, H., Benevenuto, F., Gummadi, K.: Measuring User Influence in Twitter: The Million Follower Fallacy. In: Int’l AAAI Conference on Weblogs and Social Media, ICWSM (2010)Google Scholar
  26. 26.
    Chu, Z., Gianvecchio, S., Wang, H., Jajodia, S.: Who is Tweeting on Twitter: Human, Bot, or Cyborg?. In: Annual Computer Security Applications Conference, ACSAC 2010 (2010)Google Scholar
  27. 27.
    Gao, H., Hu, J., Wilson, C., Li, Z., Chen, Y., Zhao, B.: Detecting and Characterizing Social Spam Campaigns. In: Proceedings of ACM SIGCOMM IMC, IMC 2010 (2010)Google Scholar
  28. 28.
    Griery, C., Thomas, K., Paxsony, V., Zhangy, M.: @spam: The Underground on 140 Characters or Less. In: ACM Conference on Computer and Communications Security, CCS (2010)Google Scholar
  29. 29.
  30. 30.
    Koutrika, G., Effendi, F., Gyongyi, Z., Heymann, P., Garcia-Molina, H.: Combating spam in tagging systems. In: Int’l Workshop on Adversarial Information Retrieval on the Web, AIRWeb 2007 (2007)Google Scholar
  31. 31.
    Kwak, H., Lee, C., Park, H., Moon, S.: What is Twitter, a Social Network or a News Media?. In: Int’l World Wide Web, WWW 2010 (2010)Google Scholar
  32. 32.
    Lee, K., Caverlee, J., Webb, S.: Uncovering Social Spammers: Social Honeypots + Machine Learning. In: ACM SIGIR Conference, SIGIR (2010)Google Scholar
  33. 33.
    Leskovec, J., Faloutsos, C.: Sampling from large graphs. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD (2006)Google Scholar
  34. 34.
    Stringhini, G., Barbara, S., Kruegel, C., Vigna, G.: Detecting Spammers On Social Networks. In: Annual Computer Security Applications Conference, ACSAC 2010 (2010)Google Scholar
  35. 35.
    Wang, A.: Don’t follow me: spam detecting in Twitter. In: Int’l Conferene on Security and Cryptography, SECRYPT (2010)Google Scholar
  36. 36.
    Yang, C., Harkreader, R., Gu, G.: Die free or live hard? empirical evaluation and new design for fighting evolving twitter spammers (extended version). Technical report (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Chao Yang
    • 1
  • Robert Chandler Harkreader
    • 1
  • Guofei Gu
    • 1
  1. 1.SUCCESS LabTexas A&M UniversityUSA

Personalised recommendations