On the Books: Jim Crow and Algorithms of Resistance, a Collections as Data Case Study

Abstract

On the Books: Jim Crow and Algorithms of Resistance is a collections as data and machine learning project from the University Libraries at the University of North Carolina at Chapel Hill. This project has created a plain text corpus of North Carolina legal volumes (1866-1967) and used machine learning to identify likely Jim Crow laws. The project has been well received and is now being expanded to two additional states, while assessing the use of On the Books products in research and instruction. State partners at the University of South Carolina and the University of Virginia are adapting the On the Books methodology to create corpora for their own states. Three teaching fellows created learning modules that use products from On the Books and taught the modules to college-level courses. Research fellows are making use of the products on research projects of their own design. This paper will provide background for the On the Books project and will assess its use for multiple purposes: as a workflow to be reproduced by others, as content for use in teaching and learning, and as a resource for researchers. To demonstrate the utility of On the Books as a research tool, the article is co-authored by one of the research fellows. The project, “Mental Health, Disability, and Jim Crow Laws in North Carolina, 1866-1967,” makes use of the legal corpus as a primary source for researching the intersections of information, mental health, nutrition, and shifts from agricultural to industrial economics in the history of North Carolina. By assessing the experiences of those making use of On the Books products, this paper contributes to the understanding of best practices for those interested in creating and supporting collections as data so they may be used successfully for reproducibility, research, and teaching.