Dataverse Administrator About

TurboCurator by ICPSR assists data depositors by providing recommendations for enhancing metadata quality before publication.

TurboCurator can be installed for Dataverse installations/universes that run on version 6.1 and higher.

As soon as the Dataverse dataset is created, TurboCurator can be used. Data depositors are encouraged to complete as many metadata fields as possible. While TurboCurator is intended to improve metadata prior to publication, the tool can also be used for existing published datasets.

Currently, TurboCurator should only be used for non-sensitive data.

Prior to publication, TurboCurator uses the following to improve the quality of metadata:

1. Metadata entries, e.g., title, description, subject, and keywords
2. Additional text entered in TurboCurator from research sources

TurboCurator generates recommendations powered by OpenAI’s ChatGPT technology and ICPSR’s suggestion logic. Suggestions are provided for Title, Description, and Keywords.

• Title and Description fields are automatically suggested based on ICPSR’s 60 years of experience curating and preserving data. Keywords will follow ICPSR social science thesaurus preferred terms.

Data depositors may accept, ignore or modify suggestions, or manually copy metadata recommendations back to their deposit. Metadata improvements will make it easier for others to find and reuse their data.

See our Frequently Asked Questions for more information on TurboCurator by ICPSR.

Download TurboCurator Manifest, to add TurboCurator to your Dataverse Installation.

Local Dataverse administrators can install TurboCurator in their Dataverse.

1. Download the “turbocurator.json” file
2. Run the following command: curl -X POST -H 'Content-type: application/json' http://localhost:8080/api/admin/externalTools --upload-file turbocurator.json

Note: Additional explanation is available in the Dataverse Guides