Data

The bulk of our data comes from the GDELT Project, a database which accumulates and analyzes news and media from around the world in a variety of ways. We filtered it using Google BigQuery’s SQL-like syntax (see this page for info on GDELT’s Google BigQuery hosting and this page to access the BigQuery tables), bash scripts, and python scripts with a few extra libraries.

For a few more details see the Data section of our Processbook and for all of the rest check out our Github repo.