A two-day meeting of humanities scholars, librarians, and computational analysis experts to consider how to improve existing cataloging software that attempts to better classify interdisciplinary humanities research.
Interdisciplinary research in the humanities requires indexing that represents multiple disciplinary perspectives. Most literature has been indexed using traditional models for subject analysis that are either too broad to be helpful or represent a single disciplinary perspective. We question whether traditional print models of subject analysis serve humanistic researchers' needs in working with digital content. It is beyond the capacity of libraries to re-index this body of literature relying on human indexers. We need to develop scalable tools to both re-index extant bodies of literature and newly created literature. Web-scale searching, computational text analysis, and automated indexing each hold promise for addressing various aspects of the problem, but none seem to fully address the problem. This project will gather a group of scholars with expertise in the humanities, computational analysis of texts, and library and information science, to design an approach to the problem.