Fernandez, Rachel
A collection of scholarly work created by Rachel Fernandez. https://orcid.org/0000-0002-7697-4149
Rachel is the Research Data Reproducibility Librarian, within the Open Science and Scholarly Communication Division at ASU Library. In this role, she is responsible for developing and managing research data publication workflows and providing guidance and support to the ASU research community with an emphasis on supporting reproducibility and open science practice.
Prior to joining ASU Library, Rachel worked as the Digital Preservation Program Manager for archaeological data at the Center for Digital Antiquity, which manages tDAR (the Digital Archaeological Record).
With a background in archaeology and digital preservation, Rachel is dedicated to preserving and making accessible cultural heritage data.
In summer 2024, as part of Arizona State University’s collaboration with OpenAI, the ASU Library launched a pilot project using the AI tool ChatGPT. This project aims to enhance the discoverability and curation of digital collections within the library’s repository ecosystem. The use of AI in libraries is gaining attention, with many institutions exploring AI for generating descriptive metadata. ASU Library’s extensive repository platforms, including an institutional repository, data repository, and a digital collections platform, hold approximately over 10,000 objects, with numbers expected to grow. The library lacks a dedicated position for creating metadata, with the responsibility distributed among various units already tasked with other duties. This project aims to determine whether ChatGPT can effectively generate accurate metadata that meets best practices. The library will use an existing archival collection of government documents, which already has human-created metadata, as a benchmark, in comparing the generated metadata for the fields Title, Description, and Keywords. By comparing ChatGPT-generated metadata to the existing metadata, the library will assess the relevance of AI outputs and the level of oversight required. If the AI-generated metadata shows minimal variance from the human-created metadata, the workflow could expand to other collections and reduce the backlog of unpublished archival collections that require descriptive metadata.
Purpose: To investigate the suitability of ChatGPT to facilitate discoverability and curation of digital collections within the ASU Library repository ecosystem. Our project poses the question of whether ChatGPT can positively impact our ability to generate accurate metadata that aligns with relevant best practices.
In summer 2024, as part of Arizona State University’s collaboration with OpenAI, the ASU Library launched a pilot project using the AI tool ChatGPT. This project aims to enhance the discoverability and curation of digital collections within the library’s repository ecosystem. The use of AI in libraries is gaining attention, with many institutions exploring AI for generating descriptive metadata. ASU Library’s extensive repository platforms, including an institutional repository, data repository, and a digital collections platform, hold approximately over 10,000 objects, with numbers expected to grow. The library lacks a dedicated position for creating metadata, with the responsibility distributed among various units already tasked with other duties. This project aims to determine whether ChatGPT can effectively generate accurate metadata that meets best practices. The library will use an existing archival collection of government documents, which already has human-created metadata, as a benchmark, in comparing the generated metadata for the fields Title, Description, and Keywords. By comparing ChatGPT-generated metadata to the existing metadata, the library will assess the relevance of AI outputs and the level of oversight required. If the AI-generated metadata shows minimal variance from the human-created metadata, the workflow could expand to other collections and reduce the backlog of unpublished archival collections that require descriptive metadata.