Using AI to Generate Affective Images: Methodology and Initial Library

Abstract excerpt

<p>We introduce a human-in-the-loop pipeline for creating context-aware (e.g., culture, sex, and age) affect induction images and the initial Library of AI-Generated Affective Images (LAI-GAI). Current limitations in image-based research include weak to moderate emotional elicitation effects, limited image diversity, and minimal cultural tailoring of images. Using generative AI guided by existing datasets and emot...

Topics

Open a Topic to create a Post that cites this publication.

• Artificial Intelligence
• Attention
• Cannabis and Cannabinoid Research
• Communication
• Intelligence
• Language
• Phenotype
• Prenatal Substance Exposure Effects

Identifiers and source

Literature Corpus work

62a1dc44-34ee-58bc-9312-2e41119e6cdd

DOI

10.31234/osf.io/vxb7p_v3