Exploring AI-assisted Classification for Collection Analysis
DOI:
https://doi.org/10.5860/ital.v45i3.17644Keywords:
Collection assessment, AI, LC classificationAbstract
Academic libraries face ongoing difficulty in aligning their collections with the needs of the communities they serve. Although the literature identified the value of using research, publications, and teaching data to inform collection development, maintaining crosswalks between these activities and library classification schemas made such work at scale impractical. This study developed a scalable workflow that maps institutional outputs to Library of Congress (LC) classification categories using a large language model to support an ongoing, evidence-based approval plan review. The workflow integrated six datasets across two domains of academic activity: research outputs and teaching activities. Where bibliographic metadata existed, they were used directly; otherwise, Anthropic’s Claude Sonnet inferred LC classifications through data-specific prompts. A Python pipeline combining the Claude and bibliographic metadata APIs produced enriched datasets at scale, followed by automated LC range validation and selective human review. The outputs feed a three-page interactive Tableau dashboard: a summary landing page, a Research Outputs Explorer, and a Teaching Activities Explorer. The collection development team has used the dashboard alongside expenditure and usage data to review approval plans, highlighting the value of unifying previously siloed data sources. The workflow is designed to refresh with new outputs and improved models, offering a sustainable foundation for ongoing collection assessment, including gap analysis and alignment with institutional priorities.
References
Acquisitions and Bibliographic Access Directorate of the Library of Congress, “Library of Congress Classification Outline,” Cataloging and Acquisitions, accessed April 27, 2026, https://www.loc.gov/catdir/cpso/lcco/.
Anthropic, “Models Overview,” Claude Platform Docs, accessed April 29, 2026, https://platform.claude.com/docs/en/about-claude/models/overview.
Charlene Chou and Tony Chu, “An Analysis of BERT (NLP) for Assisted Subject Indexing for Project Gutenberg,” Cataloging & Classification Quarterly 60, no. 8 (2022): 807–35, https://doi.org/10.1080/01639374.2022.2138666.
Christian Wartena and Michael Franke-Maier, “A Hybrid Approach to Assignment of Library of Congress Subject Headings,” Archives of Data Science, Series A 4, no. 1 (2018): 1–13, https://doi.org/10.5445/KSP/1000085951/22.
Eric H. C. Chow et al., “An Experiment with the Use of ChatGPT for LCSH Subject Assignment on Electronic Theses and Dissertations,” Cataloging & Classification Quarterly 62, no. 5 (2024): 574–88, https://doi.org/10.1080/01639374.2024.2394516.
Eugene Wiemers et al., “Collection Evaluation: A Practical Guide to the Literature,” Library Acquisitions: Practice & Theory 8, no. 1 (1984): 65–76, https://doi.org/10.1016/0364-6408(84)90055-3.
Fulvio Mazzocchi, “Knowledge Organization System (KOS),” in Encyclopedia of Knowledge Organization (Toronto: International Society for Knowledge Organization, November 11, 2024), https://www.isko.org/cyclo/kos#2.0.
George S. Bonn, “Evaluation of the Collection,” Library Trends 22 (January 1974): 265–304.
Jason Priem et al., “OpenAlex: A Fully-Open Index of Scholarly Works, Authors, Venues, Institutions, and Concepts,” preprint, arXiv, June 17, 2022, https://doi.org/10.48550/arXiv.2205.01833.
Jennifer Beals, “Assessing Library Collections,” Electronic Journal of Academic and Special Librarianship 7, no. 3 (2006), https://southernlibrarianship.icaap.org/content/v07n03/beals_j01.htm.
Julie Linden et al., “Collections as a Service: A Research Library’s Perspective,” College & Research Libraries 79, no. 1 (2018): 86, https://doi.org/10.5860/crl.79.1.86.
Koraljka Golub, “Automated Subject Indexing: An Overview,” Cataloging & Classification Quarterly 59, no. 8 (2021): 702–19, https://doi.org/10.1080/01639374.2021.2012311.
Kyle Morgan, “Using AI to Auto-Tag Graduate Theses,” Information Technology and Libraries 44, no. 4 (2025): 1–10, https://doi.org/10.5860/ital.v44i4.17381.
Laura M. Bartolo et al., “Collection Development and Interdisciplinary Endeavors: Collaborative Efforts for Educational and Work Environments,” presented at the ACRL Tenth National Conference, Denver, Colorado, March 15–18, 2001.
Lorcan Dempsey, “The Facilitated Collection,” LorcanDempsey.Net, January 31, 2016, https://www.lorcandempsey.net/towards-the-facilitated-collection/.
Marit Asula et al., “Kratt: Developing an Automatic Subject Indexing Tool for the National Library of Estonia,” Cataloging & Classification Quarterly 59, no. 8 (2021): 775–93, https://doi.org/10.1080/01639374.2021.1998283.
Michael Hughes, “A Long-Term Study of Collection Use Based on Detailed Library of Congress Classification, a Statistical Tool for Collection Management Decisions,” Collection Management 41, no. 3 (2016): 152–67, https://doi.org/10.1080/01462679.2016.1169964.
Nancy E. Gwinn and Paul H. Mosher, “Coordinating Collection Development: The RLG Conspectus,” College & Research Libraries 44, no. 2 (1983): 128–40, https://doi.org/10.5860/crl_44_02_128.
Roberto Carlos Morales-Hernández et al., “A Comparison of Multi-Label Text Classification Models in Research Articles Labeled with Sustainable Development Goals,” IEEE Access 10 (2022): 123534–48, https://doi.org/10.1109/ACCESS.2022.3223094.
Sarah Sutton et al., “Data-Driven Collection Development: Text Mining College Course Catalogs,” Kansas Library Association College and University Libraries Section Proceedings 14, no. 1 (2024), https://doi.org/10.4148/2160-942X.1093.
Shi-Jian Gao et al., “A Longitudinal Investigation into the Changing Citing Behavior of Geomatics Postgraduate Students at Wuhan University, China, 1988–2004: Implications for Collection Development,” Library Collections, Acquisitions, & Technical Services 31, no. 1 (2007): 42–57, https://doi.org/10.1080/14649055.2007.10766145.
Sugabsen Martins, “Artificial Intelligence-Assisted Classification of Library Resources: The Case of Claude AI,” Library Philosophy and Practice (e-Journal) (2024): 8159, https://digitalcommons.unl.edu/libphilprac/8159.
Tobias Weber et al., “Using Supervised Learning to Classify Metadata of Research Data by Field of Study,” Quantitative Science Studies 1, no. 2 (2020): 1–26, https://doi.org/10.1162/qss_a_00049.
University of Pittsburgh Library System, “General Collections Development Policy,” ULS Collections, accessed April 27, 2026, https://library.pitt.edu/collections-overview.
Weiye Gu et al., “Assessing the Alignment of University Library Collections with Scholarly Research Outputs: UW-Madison Case Study,” The Journal of Academic Librarianship 51, no. 6 (2025): 103153, https://doi.org/10.1016/j.acalib.2025.103153.
William Aguilar, “The Application of Relative Use and Interlibrary Demand in Collection Development,” Collection Management 8, no. 1 (1986): 15–24, https://doi.org/10.1300/J105v08n01_02.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Jennifer Moon-Chung, Berenika M. Webster
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors that submit to Information Technology and Libraries agree to the Copyright Notice.
