Graduate Assistant, On the Books: Jim Crow and Algorithms of Resistance

Graduate Assistant, On the Books: Jim Crow and Algorithms of Resistance

Department: Digital Research Services, University Libraries

Hours per week: 20

Salary: $19.30/hr

Dates: January 2022 – December 2023

The University Libraries is a hiring graduate assistant for the On the Books: Jim Crow and Algorithms of Resistance (OTB) project. The project has used freely available technology including Python and Tesseract OCR to create a text corpus of NC General Statutes from 1866-1967 from images available in the Internet Archive. Laws likely to be Jim Crow laws were identified using machine learning and a training set of laws classified by experts as either “Jim Crow” or “not Jim Crow”. The Jim Crow laws identified by the project are available as a plain text corpus and can be searched from the OTB website. The project website lists and contextualizes the Jim Crow laws and provides educational resources. A GitHub repository provides documented scripts generated by the project team. To read more about the project, visit the website: https://onthebooks.lib.unc.edu/

The project is currently in phase 3, with anticipated funding from the Andrew W. Mellon Foundation beginning in January 2022. Goals for this phase include expanding the project to two additional states and facilitating the use of OTB products in research and teaching. To expand the project, funds will be regranted to teams from two partner states. The partner states will create corpora for their own states and use the OTB training set to try to identify Jim Crow laws. To facilitate the use of the OTB products in research and teaching, three graduate student research fellows, two or more faculty research fellows, and three teaching fellows will be awarded funds to use OTB products (including the website, corpora, training set, algorithm, and workflows). Research fellows will use products from OTB in a research project. Teaching Fellows will create an education module using OTB products during Summer 2022 that will be taught during Fall 2022 or Spring 2023 to an undergraduate or graduate course.

The Graduate Assistant will be a member of the project team that supports this work.

 Job Duties:

  • Work with the project team to adapt the (Python and Tesseract OCR) workflow used for North Carolina laws so it can be used with laws from other states. Adapt and document code as needed.
  • Participate in monthly meetings with partner states and work with the project team to troubleshoot, solve problems, and assist partners as needed.
  • Support teaching fellows with their work. This may include answering questions as needed during module creation (working through modules and providing feedback) and serving as an assistant when teaching fellows teach the modules to their classes.
  • Participate in meetings of the teaching fellow cohort.
  • Support research fellows as needed, answering questions about the OTB products, and helping them overcome obstacles in their research. Researchers may need assistance parsing and manipulating the OTB corpora, using and adapting OTB scripts, or writing their own scripts to analyze the corpora.

Depending on the needs of partners and fellows, additional duties may include:

  • Data cleaning of structured text using Python and Excel
  • Documenting scripts in Jupyter notebooks
  • Text analysis, including supervised classification, topic modelling, and named entity recognition
  • Text transcription
  • Visualization

Required skills and experience:

  • Python Programming
  • Experience with GitHub
  • Excellent communication and problem-solving skills

Preferred skills and experience:

  • Experience working with textual data sets
  • Text analysis
  • Curriculum development
  • Research support experience

Details:

The position is for 20 hours a week, will start in January 2022, and is available through December 2023. The position is contingent upon funding.

 To Apply:

Submit a resume or CV and a cover letter describing the skills you could bring to the team and what interests you about the project to Amanda Henley (amanda.henley@unc.edu).

The University Libraries at the University of North Carolina at Chapel Hill (UNC at Chapel Hill) is committed to creating a community that is inclusive, open, and equitable for all. As an organization, we lead with trust, respect, and integrity. We embrace the contributions of every individual while also celebrating our collective achievements. The University’s founding principles—Lux, Libertas—guide our efforts to build bridges and to lead change. For more information about our related work and projects, see our Inclusion, Diversity, Equity, and Accessibility (IDEA) pages.