A Brief Summary
On the Books: Jim Crow and Algorithms of Resistance is a collections as data and machine learning project of the University of North Carolina at Chapel Hill Libraries with the goal of discovering Jim Crow and racially-based legislation signed into law in North Carolina between Reconstruction and the Civil Rights Movement (1866/67-1967).
Project outputs include:
Two publicly accessible, plain-text corpora: one of all North Carolina Session Laws from 1866/67-1967 for general legal and historical research, and one of laws determined by algorithms as likely to be Jim Crow laws. The session laws are the statutes passed during each session of a legislature, listed in the order that they were passed. A text corpus (plural form corpora) is a structured textual dataset used for text analysis.
A git repository containing documented scripts that were created for this project, for the benefit of future collections as data projects.
A short white paper describing our methods and workflows for accurate, large-scale OCR text conversion and text analysis for future teams seeking to create large-scale digital corpora and/or experiment with data-driven discovery.
This website, for educators and researchers interested in Southern and African American History, that contextualizes North Carolina segregation laws.
This project has been presented to local and national audiences, including academics, librarians, K-12 educators. Watch the recorded ASERL webinar.
In Honor of Pauli Murray
Reverend Dr. Pauli Murray was a lawyer, Episcopal priest, and human rights activist. Murray was co-founder for the National Organization for Women and author of States’ Laws on Race and Color (1951), which Thurgood Marshall called “the bible of the civil rights movement.” The book cataloged racially based laws in every state of the country, including Murray’s home state of North Carolina. In 1938, the University rejected the admission of Pauli Murray based on the color of her skin. More information about Pauli Murray is available from the Pauli Murray Project, featuring an exhibit about her life. The work of On the Books honors Pauli Murray’s legacy, building on her work researching and identifying racial codes of the Jim Crow era.
On the Books also builds on the work of legal scholar Richard A. Paschal. Paschal identified numerous Jim Crow laws in his book, Jim Crow in North Carolina The Legislative Program from 1865 to 1920. Laws identified by Paschal and Murray were included in the training set created to teach an algorithm to identify Jim Crow laws.
Algorithms of Resistance
On the Books: Jim Crow and Algorithms of Resistance uses text mining and machine learning to identify racist language in legal documents, helping expose the wide-ranging effects of Jim/Jane Crow on the American South. We have coined the phrase “algorithms of resistance” in reference to Safiya Noble’s Algorithms of Oppression: How Search Engines Reinforce Racism (2018). If algorithms can reinforce racism, could we also use algorithms to fight racism? Instead of proliferating racist ideas, can algorithms help us better study the history of race and advocate for justice?
Marrying history, social justice, and cutting-edge digital research methods requires a diverse team. The project team is predominantly from the UNC University Libraries but is heavily interdisciplinary and relies on experts in African American history, special collections, digital research, data analysis, and data visualization. Additionally, we consulted with experts in information science, legal information, optical character recognition, and text analysis.
Lorin Bruckner, Text Analysis and Visualization Expert (UNC Libraries)
Neil Byers, Research Assistant (UNC Libraries)
Sarah Carrier, Content Expert and Outreach (UNC Libraries)
Rucha Dalwadi, Research Assistant (UNC Libraries)
James Dick, Graduate Assistant (UNC Libraries)
María R. Estorino, Executive Sponsor and Liaison to the Library Leadership Team (UNC Libraries)
Grant Glass, Graduate Assistant (UNC Libraries)
Amanda Henley, Co-Principal Investigator and Project Lead (UNC Libraries)
Hannah Jacobs, Graduate Assistant (UNC Libraries)
Matt Jansen, Co-Principal Investigator, Text Analysis Expert, and Statistician (UNC Libraries)
Nathan Kelber, Senior Advisor (JSTOR Labs)
Steve Segedy, Website Developer (UNC Libraries)
William Sturkey, Disciplinary Scholar (UNC Department of History)
Kimber Thomas, African American Studies Scholar (UNC Libraries)
Student Workers (UNC Libraries)
Montana Eck, Julia Long, Ashley Mullikin, Siri Nallaparaju, Tim Oyeleke, and Jenna Patton
Additional Project Consultants and Collaborators
Daniel Anderson, Professor for Pilot Project: NC Jim Crow Laws, 1899-1919
Paul Bonnici, Manager, Carolina K-12
Ryan Cordell, OCR Specialist and author of A Research Agenda for Historical and Multilingual Optical Character Recognition
Kristen Foote, Research Assistant and Lead for Pilot Project: NC Jim Crow Laws, 1899-1919
Anna Goslen, Metadata Librarian
Aaron S. Kirschenfeld, North Carolina Legal Information Expert
Christie Norris, Director, Carolina K-12
Ryan Shaw, Information Science Expert
The work of On the Books: Jim Crow and Algorithms of Resistance has been funded by the Andrew W. Mellon Foundation as part of the first cohort for Collections as Data: Part to Whole and the ARL Venture Fund.
Interested in learning more about the project?
More to come! We are currently in the second phase of this project.