Detecting spam in a Twitter network

  • Sarita Yardi Georgia Tech
  • Daniel Romero Cornell University
  • Grant Schoenebeck UC Berkeley
  • danah boyd Microsoft Research New England
Keywords: social network analysis, microblogging, spam


Spam becomes a problem as soon as an online communication medium becomes popular. Twitter’s behavioral and structural properties make it a fertile breeding ground for spammers to proliferate. In this article we examine spam around a one-time Twitter meme—“robotpickuplines”. We show the existence of structural network differences between spam accounts and legitimate users. We conclude by highlighting challenges in disambiguating spammers from legitimate users.

Author Biographies

Sarita Yardi, Georgia Tech
PhD candidate in Social Computing at Georgia Tech
Daniel Romero, Cornell University
PhD student at the Center for Applied Mathematics of Cornell University.
Grant Schoenebeck, UC Berkeley
PhD candidate in theoretical computer science at University of California, Berkeley
danah boyd, Microsoft Research New England
Social Media Researcher at Microsoft Research New England and a Fellow at Harvard University's Berkman Center for Internet and Society.
How to Cite
Yardi, S., Romero, D., Schoenebeck, G., & boyd, danah. (2009). Detecting spam in a Twitter network. First Monday, 15(1).