CIRSS Seminar - Rescuing Lost History: Using Big Data to Recover Black Women's Lived Experiences
4pm - 5pm
Description: Big data and computational analysis are often far from neutral processes and sites unimpeded by the political, social and economic context in which they emerged and are utilized. The methods, theories, perspectives and the related digital tools developed often reproduce the social divisions that exist in society. This study is an effort to recover Black women’s history from the digital minefield by searching approximately 800,000 books, newspapers, poems, diaries and articles in the HathiTrust and JSTOR Digital Libraries between 1740 and 2014 for documents written by or about Black women. Latent Dirichlet allocation (LDA) algorithms and comparative text mining are used to explore latent themes in collections written within and across different time periods. Data visualization techniques, such as tree maps, are used to identify spikes in certain topics during various historical contexts such as slavery, reconstruction, Jim Crow, etc. The goal is to identify perceptions and lived experiences of Black women and the resulting knowledge (standpoints) that developed. In addition, we hope to create a new database with the recovered documents.
Ruby Mendenhall is an Associate Professor at the University of Illinois, Urbana-Champaign. She holds joint faculty appointments in Sociology, African American Studies, Urban and Regional Planning, Social Work and Gender and Women’s Studies. She is currently a faculty member at the Carl R. Woese Institute for Genomic Biology and a faculty affiliate at the Institute for Computing in the Humanities, Arts and Social Sciences, Women and Gender in Global Perspective, and Gender and the Cline Center for Democracy. She is the recipient of the Richard and Margaret Romano Professorial Scholar for outstanding achievements in research and leadership on campus. Mendenhall’s research focuses on racial microaggressions in higher education. She examines how living in racially segregated neighborhoods with high levels of violence affects Black mothers’ mental and physical health using surveys, interviews and genomic analysis. She studies how to recover Black women’s lost history using topic modeling and data visualization to examine over 800,000 documents from 1740 to 2014. Mendenhall also does research on the Earned Income Tax Credit (EITC).
Harriett Green is the interim Head of Scholarly Communication and Publishing, English and Digital Humanities Librarian, and associate professor, University Library, at the University of Illinois at Urbana-Champaign. Her research and publications focus on use and users of digital humanities tools and resources, digital pedagogy, digital publishing, and humanities data curation. Her research has been supported by grants awarded from the Institute for Museum and Library Services, XSEDE, and the National Endowment for the Humanities. Her current research projects include serving as Principal Investigator for the IMLS-funded "Digging Deeper, Reaching Further: Libraries Empowering Users to Mine the HathiTrust Digital Library" project and for the "Humanities Collaborations and Research Practices” project.