Publication

Enhanced archival metadata through AI: a case study of digitized photograph descriptions [Scripts]

Citations
Altmetric:
Abstract
This process provided substantial improvements over existing minimal descriptive metadata. Generated subject terms mapped successfully to the Faceted Application of Subject Terminology (FAST) vocabulary in 64% of cases, demonstrating compatibility with established standards. Post-project analysis revealed this approach to be a cost-effective method of metadata enhancement.
Description
This record contains code used to query the Anthropic’s Claude Sonnet 4 model via the API to generate descriptive metadata for a collection of 2,263 digitized archival photographs. The publication that describes this process will be published in The Electronic Library in Spring 2026.
Date
2026-01-14
Journal Title
Journal ISSN
Volume Title
Publisher
Collections
Libraries Scholarly Works
Show all metadata
Files
anthropic-api-metadata-generation.ipynb
Unknown, 19.05 KB
Research Projects
Organizational Units
Journal Issue
Keywords
Metadata enhancement, Metadata, Digital archives, Artificial intellgence
Citation
URI
https://hdl.handle.net/1808/36285
DOI
10.17161/1808.36285
Embedded videos