ACE Seminar: Data-driven Research for Advanced Modeling and Analysis or: How I Learned to Stop Worrying and Love the DRAMA

Speaker: Jeremy Blackburn

Date/Time: 30-Apr-2018, 00:00 UTC

Venue: MPEB 1.20



Over the past 20 years or so, the world has seen an explosion of data. The Web has not only shrunk the world, but also enabled the production of incredibly detailed data at a scale never before imagined. While in the past, a controlled experiment, small scale survey, or compilation of high level statistics allowed us to gain insights into the problems we explored, the Web has brought about a host of new challenges for researchers hoping to gain an understanding of modern socio-technical behavior. First, even discovering appropriate data sources is not a straight forward task. While there are obvious sources like Twitter and Facebook, there are literally millions of other Web communities that might provide more relevant data to the problem at hand. Next, although the Web enables us to collect highly detailed digital information, there are issues of availability and ephemerality: simply put, researchers have no control over what data a 3rd party platform collects and exposes ,and more specifically, no control over how long that data will remain available. Third, the massive scale and multiple formats data are available in requires creative execution of analysis. Finally, modern socio-technical problems, while related to typical social problems, are fundamentally different, and in addition to posing a research challenge, can also cause disruption in researchers' personal lives. In this talk, I will discuss how my work has overcome the above challenges. Using concrete examples from my research, I will delve into some of the unique datasets and analysis we have performed, focusing on emerging issues like hate speech/harassment campaigns and modeling the influence that Web communities have on the spread of fake news. Of particular note, I will also discuss how the modern information ecosystem exposes researchers to attacks by the very actors they study.


Jeremy is an Assistant Professor in the Computer Science Department at UAB. In a nutshell, Jeremy’s work can be described as studying jerks on the Internet and has been covered in the media by The Atlantic, Nature, the BBC, Vice, New Scientist, and MIT Technology Review, among others. Although his foundations are in large-scale distributed systems, he has spent the majority of his time measuring and understanding bad behavior on the world’s largest distributed system, the World Wide Web. His research has ranged from studying how cheating behavior spreads like a disease through a global network of online video game players, to understanding and predicting toxic behavior in the world’s most popular multiplayer video game, and more recently, understanding online hate speech, harassment campaigns, and the influence of fringe Web communities through the lens of fake news. In addition to this line of work, Jeremy has published on more traditional Computer Science topics like middlebox enabling cryptographic protocols, privacy preserving Web surfing technologies, detection of Web trackers, performance of mobile applications, Software Defined Networks, measuring the adoption of new Web protocols, and understanding human perception of Web page performance.

Add to Calendar

This page was last modified on 27 Mar 2014.