Research

Overview

I am a data scientist who studies web-based sociotechnical systems: platforms such as Google and Twitter, where humans and algorithms meet. I implement new ways to collect the digital traces that users generate while interacting with these systems and I invent new techniques for gaining meaningful insights from these traces. These insights lead to awareness about problems in existing systems and serve as a starting point to suggest new approaches, but also to advocate for more transparency from platform providers on the one hand, and sustained efforts to inform and educate users of such systems on the other.

Publications

Visit my Google Scholar page for a list of publications.

Current Projects

After the 2016 election, I have started a new research project to understand how users make decisions about what online sources to trust. My project proposal, "Signals for evaluating the credibility of web sources and advancing web literacy", received an NSF CAREER grant (2018-2023). Here is its summary:

We will experimentally test the hypothesis that when users are presented with search results that are augmented with signals for evaluating the credibility of web sources, they will strengthen their critical thinking skills and become better consumers of online information. Evaluating the credibility of web sources is a crucial critical thinking skill in our digitally mediated world. We have learned to rely on search engine platforms to show us the right results, while forgetting that algorithms are biased or that they can be manipulated. This research aims to discover whether and how humans can reclaim their agency when deciding what information sources to trust. Additionally, it will: (1) identify a set of human-understandable signals that are deemed helpful for evaluating the credibility of web sources and validate them through users studies; (2) propose and implement algorithmic techniques for computing some of these signals, providing a trail of transparency about how they work, and (3) develop a novel web platform for the interactive exploration of signals, modeled upon nutrition fact labels, that will contribute in advancing web literacy skills in the broad public.

Past Projects

Misinformation on the Web: During 2008-2014, I collaborated with Prof. Takis Metaxas, Samantha Finn '12 and a large number of Wellesley students in studying how rumors or other kinds of information spread in social networks like Twitter. Our research led to the creation of TwitterTrails, an online tool for reporters and everyone else interested in the origin and spread of false or true information. More information about this research can be found in Trails of Propagation website.

Data Science for Education and Learning: Since 2013, I have also been studying sociotechnical systems that enable online learning at a large scale. In one of these projects, I have been collaborating with Prof. Franklyn Turbak, Maja Svanberg ‘18, and Isabelle Li '20 to understand how people learn to program in the MIT App Inventor online platform, which has millions of users. I also have studied engagement in MOOC courses and computational thinking practices as documented by use of Jupyter notebooks.

Meetings

June 25-28, 2017, WebSci'17

Presented the paper The Fake News Spreading Plague: Was it Preventable?

May 22-24, 2017, FLAIRS'17

Presented the paper Identifying Original Projects in App Inventor.

May 15, 2017, ICWSM'17

Invited panelist at the Digital Misinformation Workshop.