Data · dataset · 2024
Racial Bias in AI-Generated Images
Listed in DANS Data Station Social Sciences and Humanities and ODISSEI Portal — shown once because both records carry DOI 10.17026/ss/7mqv4m
This file is supplementary material for the manuscript Racial Bias in AI-Generated Images, which has been submitted to a peer-reviewed journal.
Description
This dataset/paper examined the image-to-image generation accuracy (i.e., the original race and gender of a person’s image were replicated in the new AI-generated image) of a Chinese AI-powered image generator. We examined the image-to-image generation models transforming the racial and gender categories of the original photos of White, Black and East Asian people (N =1260) in three different racial photo contexts: a single person, two people of the same race, and two people of different races.
Links
Where it is published
- Dataverse dataset page ssh.datastations.nl/dataset.xhtml?persistentId=doi%3A10.17026%2FSS%2F7MQV4M ↗
landing page · from ssh datastations nl
- Dataverse dataset page portal.odissei.nl/dataset.xhtml?persistentId=doi%3A10.17026%2FSS%2F7MQV4M ↗
landing page · from portal odissei nl
- DOI doi.org/10.17026/ss/7mqv4m ↗
DOI / persistent id · from ssh datastations nl
Catalogue records · 2
- Dataverse API ssh.datastations.nl/api/datasets/:persistentId/?persistentId=doi%3A10.17026%2FSS%2… ↗
metadata API · from ssh datastations nl
- Dataverse API portal.odissei.nl/api/datasets/:persistentId/?persistentId=doi%3A10.17026%2FSS%2… ↗
metadata API · from portal odissei nl
Topics
- Stated by source
- Social Sciences · Social Sciences
- From keywords
- Humanities · Social Science · Social Science
- Inferred from text
- Image 75%
Related
- Possibly the same asRacial Bias in AI-Generated Images
Provenance · 2 source records, 12 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| DANS Data Station Social Sciences and Humanities | doi:10.17026/SS/7MQV4M | 9 d ago | JSON v1 |
| ODISSEI Portal | doi:10.17026/SS/7MQV4M | 6 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| concepts[field].dataverse_subject:social-sciences | source · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 | /subjects |
| concepts[field].dataverse_subject:social-sciences | source · portal odissei nl | connector:portal_odissei_nl@1.0.0 | /subjects |
| concepts[field].local:field:humanities | mapping · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 | /subjects |
| concepts[field].local:field:social-science | mapping · portal odissei nl | connector:portal_odissei_nl@1.0.0 | /subjects |
| concepts[field].local:field:social-science | mapping · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 | /subjects |
| concepts[modality].local:modality:image | enrichment · ssh datastations nl | keyword-concept-rules@1.0.0 | title+description (75%) |
| created_date | source · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 | |
| description | source · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 | /description |
| publication_date | source · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 | |
| title | source · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 | /name |
| updated_date | source · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 | |
| version_label | source · ssh datastations nl | connector:ssh_datastations_nl@1.0.0 |