Kindles, card catalogs, and the future of libraries: a collaborative digital humanities project

Abstract

Purpose This paper aims to determine if the digital humanities technique of topic modeling would reveal interesting patterns in a corpus of library-themed literature focused on the future of libraries and pioneer a collaboration model in librarian-led digital humanities projects. By developing the project, librarians learned how to better support digital humanities by actually doing digital humanities, as well as gaining insight on the variety of approaches taken by researchers and commenters to the idea of the future of libraries. Design/methodology/approach The researchers collected a corpus of over 150 texts (articles, blog posts, book chapters, websites, etc.) that all addressed the future of the library. They ran several instances of latent Dirichlet allocation style topic modeling on the corpus using the programming language R. Once they produced a run in which the topics were cohesive and discrete, they produced word-clouds of the words associated with each topic, visualized topics through time and examined in detail the top five documents associated with each topic. Findings The research project provided an effective way for librarians to gain practical experience in digital humanities and develop a greater understanding of collaborative workflows in digital humanities. By examining a corpus of library-themed literature, the researchers gained new insight into how the profession grapples with the idea of the future and an appreciation for topic modeling as a form of literature review. Originality/value Topic modeling a future-themed corpus of library literature is a unique research project and provides a way to support collaboration between library faculty and researchers from outside the library.

From Digital Library to Open Datasets

“…Simply put, "topic modeling is an automatic way to examine the contents of a corpus of documents." 10 The output of these models is word clouds with varying sizes of words based on the number of co-occurrences within the corpus; larger words indicate more occurrences and smaller ones indicate fewer. Each topic model then points to the most relevant documents within the corpus based on the co-occurrences of the words contained in that model.…”