Rescuing Lost History: Using Big Data to Recover Black Women's Lived Experiences

This study employs Latent Dirichlet allocation (LDA) algorithms and comparative text mining to search 800,000 periodicals in JSTOR (Journal Storage) and HathiTrust from 1746 to 2014 to identify the types of conversations that emerge about Black women's shared experience over time and the resulting knowledge that developed called standpoint We used MALLET to interrogate various genres of text (poetry, science, psychology, sociology, African American Studies, policy, etc.). We also used comparative text mining (CTM) to explore latent themes across collections written in different time periods by analyzing the common and expert models. We used data visualization techniques, such as tree maps, to identify spikes in certain topics during various historical contexts such as slavery, reconstruction, Jim Crow, etc. We identified a subset of our corpus (20,000) comprised of articles about or by or Black women and compared patterns of words in the subset against the larger 800,000 corpus. Preliminary findings indicate that when we pulled 300,000 volumes, about 800,000 (~27%) do not have subject metadata. This appears to suggest that if a researcher searched for volumes about Black women, they may not have access to a significant amount of data on the topic. When volumes are not tagged properly, researchers would have to know that these texts exists when they do their searches. The recovery nature of this project involves identifying these untagged volumes and making the corpus publicly available to librarians and others with copyr. considerations.