Integrating Artificial Intelligence into Library Metadata Workflows: A Case Study from UCF

Integrating Artificial Intelligence into Library Metadata Workflows: A Case Study from UCF

This presentation explores the use of artificial intelligence to enhance metadata creation and management at the University of Central Florida. Focusing on the automated generation of FAST subject headings for institutional repository and library collections, the session will highlight the evolution of the project from early OpenAI-based workflows to more advanced vector database solutions. Attendees will learn about the implementation process, challenges of integrating AI into cataloging workflows, and future opportunities for AI-driven metadata enrichment.

Deng, Sai

2026-04-24

This item is protected by copyright but is made available here under a claim of fair use (17 U.S.C. Section 107) for non-profit research and educational purposes. Users of this work assume the responsibility for determining copyright status prior to reusing, publishing, or reproducing this item for purposes other than what is allowed by fair use or other copyright exemptions. Any reuse of this item in excess of fair use or other copyright exemptions requires express permission of the copyright holder.

application/pdf

eng

Text; Document; Presentation

This session explores the practical implementation of Artificial Intelligence (AI) to streamline and enrich metadata workflows at the University of Central Florida. The presentation details a multi-stage initiative aimed at automating the generation of Faceted Application of Subject Terminology (FAST) subjects for diverse collections within both an institutional repository and the Alma library service platform. Attendees will gain insight into the technical transition from initial experiments—utilizing the OpenAI API alongside OCLC FAST reconciliation—to a more sophisticated architecture employing a Vector Database for enhanced precision. The speaker will discuss the current status of these AI projects, address the challenges of integrating Large Language Models (LLMs) into traditional cataloging environments, and share possible steps for future AI-driven metadata enhancements.

2026-04-24

2026-04-24

Deng, S., Piascik, J., Chow, E.H.C. & Zhu, L.H. (2025). AI subject generation: Alma AI Metadata Assistant vs. UCF’s custom AI. ELUNA Conference 2025, June 20, 2025, Atlanta, Georgia. Retrieved from:https://doi.org/10.7273/000007335

Deng, S., Piascik, J. & Zhang, Y. (2025). Optimizing metadata workflows with AI: Insights from UCF Libraries. Teaching & Learning with AI Conference, May 30, 2025, Orlando, FL. Retrieved from: https://stars.library.ucf.edu/teachwithai/2025/friday/38/

Deng, S., Piascik, J., Chow, E.H.C., Zhu, L.H. & Zhang, Y. (2025). AI in Action: reimagining metadata and cataloging with Chatbots and OpenAI. American Library Association LibLearnX Conference, January 23, 2025, Phoenix, Arizona. Retrieved from:https://doi.org/10.7273/000007124

Deng, S., Piascik, J., Chow, E.H.C., Zhu, L.H. & Zhang, Y. (2024). Transforming metadata workflows with AI: a case study at UCF Libraries. 2024 AI4Libraries Conference, October 22, 2024. Retrieved from:https://doi.org/10.7273/000006887

Deng, S., Piascik, J., Chow, E. H. C., Heng, G., Li, M. Y., Chen, S.Z., Li, X. L., Zhu, L. H. & Jiang, J. (2024). Leveraging AI for workflow enhancement in Technical Services: Case studies from US and Hong Kong libraries. Teaching & Learning with AI Conference, Orlando, Florida. July 23, 2024. https://ir.cala-web.org/items/show/1428

Deng, Sai