Google and ProPublica team up to build a national hate crime database

Few things are certain in 2017’s fraught national climate, but hate certainly doesn’t look to be going away. In partnership with ProPublica, Google News Lab is launching a new tool to track hate crimes across America. Powered by machine learning, the Documenting Hate News Index will track reported hate crimes across all 50 states, collecting data from February 2017 onward.

Data visualization studio Pitch Interactive helped craft the index, which collects Google News results and filters them through Google’s natural language analysis to extract geographic and contextual information. Because they are not catalogued in any kind of formal national database, a fact that inspired the creation of the index to begin with, Google calls the project a “starting point” for the documentation and study of hate crimes. While the FBI is legally required to document hate crimes at the federal level, state and local authorities often fail to report their own incidents, making the data incomplete at best.

“It is one of the first visualisations to use machine learning to generate its content using the Google Natural Language API, which analyses text and extracts information about people, places, and events,” Google News Lab Data editor Simon Rogers writes in the announcement. “In this case, it helps reporters by digging out locations, names and other useful data from the 3,000-plus news reports – the feed is updated every day, and goes back to February 2017.”

The initiative is a data-rich new arm of the Documenting Hate project which collects and verifies hate incidents reported by both individual contributors and by news organizations. The Hate News Index will keep an eye out for false positives (casual uses of the word “hate” for example), striking a responsible balance between machine learning and human curation on a very sensitive subject. Hate events will be mapped onto a calendar in the user interface, though users can also use a keyword search or browse through algorithmic suggestions. For anyone who’d like to take the data in a new direction, Google will open sourced its data set, making it available through GitHub.

The project’s hope is that journalists can harness its combination of visualized data and news indexing to report more effectively on the aggregate data and incidents that might otherwise fall through the cracks.