Over two years ago, a North Carolina high school social studies teacher asked the librarians at Wilson Library for a list of the state’s Jim Crow laws. When librarians responded to the request, they found there was no such list.
Since 2019, University Libraries’ On the Books: Jim Crow and Algorithms of Resistance project has used machine learning technology to digitize every law passed in N.C. during the Jim Crow era and has identified a comprehensive list of Jim Crow laws.
The multi-disciplinary team of UNC legal experts, historians and library specialists used text mining to discern and compile legislation passed between the Reconstruction Era and the Civil Rights Movement.
Now, the team is expanding the initiative with the support of a $400,000 grant from the Andrew W. Mellon Foundation.
“That kind of delved into a classic librarian’s approach to it — of trying to find that resource that existed, and finding that there really weren't very many comprehensive resources,” said Matt Jansen, co-principal investigator on the project and data analysis librarian. “And asking the question, ‘Is this a gap we can help fill?’”
Jim Crow laws refer to statutes that enacted or allowed segregation and white-supremacist legislation. Primarily based in the American South, these laws were significant instigators of the Civil Rights Movement in the 1950s and '60s.
The project is the first of its kind, said Project Lead and Principal Investigator Amanda Henley.
“We gathered a bunch of laws and we labeled them as either ‘Jim Crow’ or 'not Jim Crow,’” said Henley, who also serves as head of digital research services for University Libraries. “And we did this using existing research and also by scholars going through and deciding on a case-by-case basis if it was a Jim Crow law or not, for a random selection of the laws.”
The team then used the data from that random selection to generate an algorithm for computers to use in qualifying every Jim Crow law. The team has completed the full list for North Carolina and found nearly 2,000 laws.
“Other parts of the project have been to kind of put these laws into perspective and provide some education resources,” Henley said. “And to put the laws on a website so people can search through them.”
The project honors lawyer and activist Pauli Murray, who was denied admission to the UNC graduate school in 1938 for being a Black applicant. Murray wrote "States’ Laws on Race and Color" (1951), a book cataloging racially-based laws across the country.
"I do want to call out and put some recognition on the work that Pauli Murray did back in the 1950s — manually going through and using indexes and looking at physical volumes, and doing what was the state of the art, the best you could do at the time,” Jansen said. “We are expanding this into a computational form, and we really can go through law by law.”
On campus, the history department, along with the sociology, political science and peace, war and defense departments, has also started the process of renaming Hamilton Hall after Murray. The departments sent their proposal for Pauli Murray Hall to Chancellor Kevin Guskiewicz in July 2020.
With the support of The Andrew W. Mellon Foundation grant, the On the Books team plans to share their machine learning resources with other research teams and expand to two more states. The grant will also support research and teaching fellowships for work surrounding Jim Crow in higher education.
“One of the things that's gonna be really interesting, when we have other states do the same thing, is that now we can see how states spoke with each other,” said William Sturkey, the project’s scholarly lead and associate professor in the Department of History. Sturkey's research specializes in the history of race in the American South.
The On the Books team put out a request for proposals from other states, but has yet to select the two teams they will fund to build out the project in additional states.
Sturkey said the implications for the project are endless.
“What's innovative here is not just that we're the first people to ever put together this list of laws,” he said. “But it's really innovative in its methodology, in that it doesn't just have to be Jim Crow laws and it doesn't have to be laws about race. But the way that they've engineered this machine learning technology, you could take this to a number of different states and study any number of types of laws.”
To get the day's news and headlines in your inbox each morning, sign up for our email newsletters.