Algorithms of Resistance
Using machine learning to identify racist language in state laws
Using machine learning to identify racist language in state laws
The University Libraries at Carolina have an extensive collection of North Carolina laws and documents that is an extraordinary resource for teachers within our community — but sifting through the collection in search for commonalities is not easy.
Thanks to an interdisciplinary team of librarians and subject matter experts, a new project, On the Books, is going to fix this problem. The first iteration of this project, On the Books: Jim Crow and Algorithms of Resistance, went live in August 2020 and uses text mining and machine learning to identify racist language in legal documents.
The first iteration of this project compiled Jim Crow laws in North Carolina into one single body, which allows teachers and students alike to clearly see the extensive scope of such laws in the American South. By providing a way for the community to easily view the language within all of these documents, the University Libraries is helping people understand the history of race in America.