Uncovering the Arab Spring with a data mining approach
In 2011, the unforeseen outbreak of mass social movements in Middle East caught the U.S. government and Arab regimes completely by surprise. The ensuing political contagion, known as the Arab Spring, was in many ways played out on the stage of popular social networks, such as Twitter and Facebook.
The Arab Spring raised a critical question: Can social network data be used to better understand, and even predict, outbreaks of mass protest movements?
In this collaborative project, Robert Kubinec and Congyu Wu used a massive database of tweets collected from Arab Twitter users during the first six months of the Arab Spring, covering hundreds of protest events. They employed a statistical computer model to examine popular grievances expressed on Twitter and their connection to later outbreaks of protest activity.
Kubinec and Wu’s research explored how the Twitter network foreshadowed mass unrest and how it was used to build and sustain momentum among pro-democracy movements. The complex nature of these online networks illustrates the challenges of Big Data while promising to shed light on a subject never before studied in such detail: the anatomy of a revolution.
Robert Kubinec is a PhD student in the Department of Politics. His research interests focus on democratization in the Middle East and the interplay between governing elites and nascent social movements in the region.
Congyu “Peter” Wu is a PhD student in the Department of Systems and Information Engineering and a member of the Predictive Technology Laboratory. His research interests include data mining, machine learning, natural language processing and social media analytics.