2024
- Talk Summary: Dr. Vishwanath on Science Communication & Misinformation
Notes from a talk By Vish Vishwanath (Harvard School of Public Health; Dana-Farber Cancer Institute), hosted by David Lazar and the Internet Democracy Initiative, December 18, 2024.
- AI-Powered Content Audits for Local News
Organizations across the news industry are exploring ways to use generative AI to support their storytelling (many shared on this very blog). A growing trend is to use these new tools on the other end of the production cycle, to support content audits that assess a large set of stories ...
- Computation + Journalism 2024 Symposium wrap-up
We recently co-hosted the Computation + Journalism Symposium 2024 at Northeastern, bringing together academics, journalists, data scientists, editors, and more to explore innovate work at the intersection of fields. Keynotes from Julia Angwin, Aaron Sankin, and Alan Mislove.
- Pre-print: Comparing Author Extraction Libraries
How effective are existing tools for extracting author information from global online news? Author extracton is a key task in media research that supports a number of different types of research questions. We’ve hesitated to support this broadly in Media Cloud, because our past evaluati...
- How can AI help us study the news? Here are my experiments with LLM-based query generation.
To understand politics, economics, events and health communication in the news, researchers study large sets of articles from online news sources. Media Cloud, a project that I co-lead, holds a historical archive of over 1.5 billion stories from over 100,000 sources and has been used to...
2023
- A New Tool To Help Understand Partisan News in the US
The latest Zelda game is being covered a lot more in Democrat-serving online news sites. That’s one of the first random tidbits I noticed in “On Our Own Terms”, a new tool built by Claire Pan and I as part of the Media Could project.
2022
- Upcoming AMC FAccT Talk: Towards Intersectional Feminist and Participatory ML
We’ll be presenting our collaborative work on the Data Against Feminicide project at the 2022 ACM Conference on Fairness, Accountability and Transparency. We’re very excited to put forward this work as a case study in intersectional feminist and participatory approaches to machine learn...
- Upcoming talk at PaCSS'22: Partisan Media Coverage and Intersectionality
I’ll be speaking at the 2022 Politics and Computational Social Science conference today with my colleague Meg Heckman. We’ll be presenting work, with Emily Boardman Ndulue, that took an intersectional lens to analyzing how online news media covered the election of current US Vice Presid...
- Helping Computers Find Food in Text
Computers are good at processing large amounts of information, but bad at intuiting what that information actually is. For an ongoing research project looking at mentions of food in online media, we’re trying to help computers get better at recognizing entities in unstructured text. Giv...
- Understanding the 2020 “Racial Reckoning” In the Media
Just over two years ago, on May 25th, 2020, George Floyd was murdered by Minneapolis police officer Derek Chauvin. The shocking video of the incident quickly circulated across the internet through social media. Mr. Floyd’s murder sparked countless protests across the country and globe ...
- Upcoming Talk at C+J'22 Conference: News as Data for Activists
I’ll be speaking at the 2022 Computation + Journalism conference, hosted at Columbia University from June 9-11. I’ll be presenting a paper on the software architecture supporting the Data Against Feminicide project.
- ICA'22 Poster: Politicization and Polarization of Pandemic News Coverage
I’m excited to join a large team of Northeastern collaborators to present ongoing work at the International Communication Association 2022 Conference. I supported the data acquisiton and analysis pieces of this work by Larissa Doroshenko, Ryan Gallagher, Shreya Singh, and Brook Foucault...
2021
- Finding Tweets in Online News
The use of embedded content from Twitter, YouTube, TikTok, and other platforms has grown to become a norm in online news content. When these platforms emerged journalists employed existing industry norms to treat them like traditional sources - content that needed verification, vetting,...
- Swiped: How dating apps harm marginalized communities
We started out investigating media coverage of LGBTQ+-specific data breach issues, yet race and racism are unavoidable. Potential harms from online dating apps are constant, but our attention to these issues should extend far beyond the pandemic.
2020
- Pandemic news coverage is falling, but cases keep rising
The Covid-19 pandemic has yielded unprecedented media coverage. Over the last six months, no single topic has taken over online news quite like the coronavirus has. In fact, at its peak in late March, almost 75% of all stories in top U.S. online media sources mentioned coronavirus in so...