Algorithms of Resistance
Using machine-learning to identify historically racist laws
Using machine-learning to identify historically racist laws
From centering stories of the South’s history on the enslavedOpens in new window to preserving audiovisualsOpens in new window of historical materials from the south, UNC-Chapel Hill’s University Libraries has taken many measures to unpeel racism’s history in the South. Their latest attempt involves the use of machine-learning. Thanks to a grant of $400,000 from The Andrew W. Mellon Foundation, as well as funding from the ARL Venture Fund and from the University Libraries’ internal IDEA Action grants, experts at the University Libraries are extending their investigation of the use of machine-learning to identify racist laws from North Carolina’s past to two more states.
This project team includes librarians, technologists and data experts who created machine-readable versions of all North Carolina statutes from 1866 to 1967 and then trained an algorithm to identify racist language in the laws.
“We’ve gained a tremendous amount of knowledge through this project,” said Henley, principal investigator for the “On the Books: Jim Crow and Algorithms of Resistance” project and head of digital research services. “We’re eager to share what we’ve learned and help others build upon it.”
