Institute-incubated Research Leveraged for Major Google Research Award

in ECE Spotlight Faculty, ECE Spotlight-Research, ENG Spotlight Faculty, NEWS, SE Spotlight Faculty, SE Spotlight-Research, Spotlight Faculty

The following article was published on the Hariri Institute’s website on Friday, March 16th, 2018.

To see the complete list of 2017 award recipients, please visit Research at Google.

What began as a small, Hariri Institute seed-funded research project to explore new methods for analyzing social media data has grown into a Google-sponsored, award-winning research endeavor.

Lei Guo, Hariri Junior Faculty Fellow and Assistant Professor of Emerging Media Studies, received a Hariri Research Incubation award in June of 2016 to pursue her proposal, Statistically Principled and Scalable Computational Tools for Transforming Communication Research. Working with co-PIs Prakash Ishwar (former Junior Faculty Fellow & Associate Professor, ECE, SE) and Margrit Betke (former Institute Steering Committee member & Professor, CS) and collaborators Jacob Groshek (Junior Faculty Fellow & Assistant Professor, Emerging Media Studies) and Dino Christenson (Faculty Fellow & Associate Professor, Political Science), the initial project aimed to explore reliable methods of analyzing big data in social contexts in communication research, analyzing ways to detect topics on Twitter and other social platforms. Hailing from four very different departments, the team of researchers found support for their cross-disciplinary research at the Hariri Institute for Computing. Betke and Guo connected at Guo’s “Meet Our Fellows” presentation that she gave after being appointed a Junior Faculty Fellow at the Institute.

Fast forward two years, and the team is now leveraging their initial work to solicit support for follow-on research. Led by PI Margrit Betke — working with co-PIs Guo and Ishwar — the goal of the Google-sponsored project is to develop machine learning and human computing methods for news aggregators to ensure that they present balanced real-time content representing diverse political perspectives to their users. The research aims to not just identify and analyze left- and/or right-leaning content, but content that samples the full political landscape in the US. The proposal is a winner of the 2017 Google Research Award in the “Information Retrieval and Real Time Content” category.

The Hariri Institute for Computing selectively seed funds new collaborations that cross typical disciplinary boundaries as well as support ambitious research and forward-looking education initiatives. Current and previously funded projects represent a broad array of the exciting new computing-related and data-driven research happening across the BU community.