Detecting Spam in a Twitter Network

Sarita Yardi, Danial Romero, Grant Schoenebeck, danah boyd


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.


 [ back to Grant's homepage]