HathiTrust Research Center (HTRC) has selected four projects to participate in its special round of Advanced Collaborative Support (ACS), funded by the Andrew W. Mellon Foundation through the Scholar-Curated Worksets for Analysis, Reuse & Dissemination (SCWAReD) project.
The projects will seek to build HTRC worksets drawn from materials related to historically under-resourced and marginalised textual communities, and in doing so, to identify gaps in the HathiTrust collection where such communities are not represented in the digital library. The worksets will be analysed using text and data mining techniques. The worksets, derived data outputs, and associated documentation will be shared at the end of the projects as illustrative research models of the text and data mining process. The four research models will join a flagship model that is being developed concurrently in collaboration with co-PI Maryemma Graham and her History of Black Writing project at the University of Kansas.
The four awarded projects are: Mining the Native American Authored Works in HathiTrust for Insights, The Black Fantastic: Curated Vocabularies, Artifact Analysis and Identification, Creating Period-Specific Worksets for Latin American Fiction, and The National Negro Health Digital Project: Recovering and Restoring a Black Public Health Corpus.
The project, Mining the Native American Authored Works in HathiTrust for Insights, seeks to compile a collection of Native American authored works in HathiTrust and apply various text mining methods to the collection to reveal the coverage, subjects, perspectives, and writing styles of Native authors. A list of Native authors and their works will be compiled from an existing database created by a member of the project team and from other online resources. The list will be aligned with the HathiTrust digital library to create a workset of Native American authored works in HathiTrust for further analysis. Then, a variety of text mining methods will be used to analyse the subjects, topics, language use, and writing styles of Native American authors. Comparative analysis will be carried-out to understand the characteristics of the textual community. The project is expected to develop a database of Native American authors and the bibliographic information of their works, create a reusable workset of Native American authored works in HathiTrust, identify potential gaps in the HathiTrust corpus on the textual community, and provide insights into the characteristics of the community by text mining their works.
The project, The Black Fantastic: Curated Vocabularies, Artifact Analysis and Identification, focuses on identifying Black Fantastic texts in the HathiTrust Digital Library. The project proposes that characteristics of the Black Fantastic—the cultural production of African Diasporic artists and creators who engage with the intersections of race and technology in their work—exist in historical and current cultural artifacts, including those created by and about future-forward personalities, such as Dr. Mary McLeod Bethune. It builds on previous and ongoing work to create a bibliography of the Black Fantastic that is featured in Third Stone Journal.
The project, Creating Period-Specific Worksets for Latin American Fiction, seeks to create large datasets to research the history of Latin American fiction and question traditional periodisation of the literature by attempting to detect the boundaries between literary periods and subgenre distinctions in Latin American fiction. It will look critically at the techniques for detecting genre distinctions that have developed over the last few years and evaluate how they apply to the particular development of Latin American literary system.
The project, The National Negro Health Digital Project: Recovering and Restoring a Black Public Health Corpus, draws on HathiTrust’s collection of public health documents on Black health to explore how early twentieth Black public health officials communicated and addressed health disparities that impacted African American communities. The major goal of the project is to create a series of worksets and visualisations that scholars and students of African American health and medicine along with public health experts and physicians can use to deepen historical narratives about Black health that might offer insight into the development of contemporary health communications targeted toward African American communities. The project also establishes some of the research for Technologies of Recovery: Black DH Theory and Praxis, a book in- progress. Finally, the work will fill a gap in the history of African American public health.
Click here to read the original press release.
