Project description

We worked to cover the release of Russian Facebook Ads by congress. We enabled a network-wide collboration, made the ads searchable, and explained their importance to readers.

What makes this project innovative?

Distributed data analysis, rapid ingestion and analysis. One of first tests of a new story form ‘explainer’.

What was the impact of your project? How did you measure it?

Extended engagement time, succsful cross-country collaboation.

Source and methodology

Ads released by congress via Facebook. USA Today network analysis. Once we learned that congress planned to release ads deemed by Facebook to have been part of a Russian disinformation campaign on their platform, we sprung into action. The data team preapred a simple internal tool that would allow a group of journlaists to review, tag, comment on, and organize the ads manually. Meanwhile, the graphics desk worked with the dataset generated to create a series of visualizations explaining what we found. Finally, we used PDF scraping, and optical character recognition to create a filterable database of all ads, so readers could see them for themselves.

Technologies Used

Python, Javascript, optical character recogition, PDF scraping, Postgres DB.

Project members

Mitchell Thorson, Ramon Padilla, George Petras, Shawn Sullivan, Pim Linders, Jim Sergent.


Additional links


Click Follow to keep up with the evolution of this project:
you will receive a notification anytime the project leader updates the project page.