Sloan Develops Algorithm To Spot Likely ISIS Members on Twitter
MIT Sloan recently looked into how a Ph.D. candidate and 15-year Army veteran Christopher Marks, along with KDD Career Development Professor in Communications and Technology Tauhid Zaman, built a machine-learning model that identifies likely Islamic State of Iraq and Syria (ISIS) members on Twitter.
According to an article from Dylan Walsh, the model that Zaman and Marks created can “detect more than half of known ISIS accounts simply by studying characteristics of the profile and patterns in its network.”
The duo initial compiled sets of data from more than 1.3 million ISIS-affiliated Twitter users, which included basic stats like “location, screen name and profile picture” by combing through “news stories, blogs and reports released by law enforcement agencies and think tanks.”
Over the course of several months, Zaman and Marks monitored Twitter and uncovered roughly 60,000 suspended or shuttered accounts with ISIS connections. Zaman explains, “We wanted to know if you can look at an account and predict it is ISIS before they say anything … because, once they do, it’s usually something bad, like the address of a soldier.”
According to Walsh, the duo also addressed the issue of detecting “users who create new accounts when their old one has been suspended.” Zaman and Marks used their algorithm to test “the similarity of the account name and profile picture against cancelled accounts to gauge the likelihood that the person under scrutiny had previously operated a suspended account.” Zaman explains, “When someone comes back he might change his name and his picture, but he’ll generally hang around the same neighborhood.”
Zaman believes their project offers “a coherent system to police these online ecosystems,” but one that certainly has its own set of ethical dilemmas attached to it.
“In the ideal case, it’s used by benevolent governments to protect people from these kinds of violent groups. It’s a tool that we developed as scientists, but in the end it’s up to the people in positions of power to use it responsibly.”
About the Author
Jonathan Pfeffer
Jonathan Pfeffer joined the Clear Admit and MetroMBA teams in 2015 after spending several years as an arts/culture writer, editor, and radio producer. In addition to his role as contributing writer at MetroMBA and contributing editor at Clear Admit, he is co-founder and lead producer of the Clear Admit MBA Admissions Podcast. He holds a BA in Film/Video, Ethnomusicology, and Media Studies from Oberlin College.
