Text Mining for Type of Research Classification. Issue 8 (25th October 2021)

• Record Type: Journal Article
• Authors: Lowe, David B.; Dollinger, Ian; Koster, Tristan; Herbert, Bruce E.
• Is Part Of: Cataloging & classification quarterly. Volume 59:Issue 8(2021)
• Page Start: 815
• Page End: 834
• Publication Date: 2021-10-25
• Subjects: Text mining -- type of research classification -- cataloging for digital resources -- BERT (Bidirectional Encoder Representations from Transformers) -- project-based learning; Cataloging -- Periodicals; Classification -- Books -- Periodicals; 025.3
• DOI: 10.1080/01639374.2021.1998281
• Languages: English
• ISSNs: 0163-9374

Abstract

Abstract: This project brought together undergraduate students in Computer Science with librarians to mine abstracts of articles from the Texas A&M University Libraries' institutional repository, OAKTrust, in order to probe the creation of new metadata to improve discovery and use. The mining operation task consisted simply of classifying the articles into two categories of research type: basic research ("for understanding, " "curiosity-based, " or "knowledge-based") and applied research ("use-based"). These categories are fundamental especially for funders but are also important to researchers. The mining-to-classification steps took several iterations, but ultimately, we achieved good results with the toolkit BERT (Bidirectional Encoder Representations from Transformers). The project and its workflows represent a preview of what may lie ahead in the future of crafting metadata using text mining techniques to enhance discoverability.