Work

Metadata augmentation for social science datasets using Generative AI

Year: 2026
Type: article
Abstract: Efficiently curating metadata with controlled terminology is a critical yet time-consuming task in social science data management and archiving. Data depositors often provide insufficient metadata, compelling data repository staff to extensively enhance the metadata. This process traditionally involves navigating a wide array of controlled terms, a task demanding substantial time and expertise, sometimes necessitating the creation of new terms. Addressing these challenges, we introduce an innovative model employing Generative AI technology (ChatGPT) coupled with a web application. This tool is engineered to complement the knowledge of the human experts who are responsible for generating metadata by presenting them with keyword suggestions from controlled vocabularies. This reduces the burden on individual data curators who prepare data collections for archiving by giving them a starting point when selecting keywords. It achieves this by rapidly analyzing text and extracting pertinent keywords from established thesauri, including the ICPSR Subject Thesaurus, the European Language Social Science Thesaurus (ELSST), Library of Congress Subject Headings (LCSH), and Medical Subject Headings (MeSH), along with ChatGPT's intelligent recommendations. This approach expedites the curation process and augments the terms selected.
Language: English
Open Access status: diamond
OpenAlex ID: W7214747465
FWCI:
Cites: 1
Cited by:
Related to: 10