ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture

TL;DR

ArtELingo is a large, multilingual dataset of artworks with emotion annotations across diverse languages and cultures, enabling research on cultural differences and improving captioning models.

Contribution

It introduces a new diverse, multilingual dataset with extensive emotion annotations, expanding beyond English to facilitate culturally-aware AI research.

Findings

Diversity enhances baseline captioning model performance.

The dataset enables cross-cultural and multilingual analysis.

ArtELingo is publicly available for research use.

Abstract

This paper introduces ArtELingo, a new benchmark and dataset, designed to encourage work on diversity across languages and cultures. Following ArtEmis, a collection of 80k artworks from WikiArt with 0.45M emotion labels and English-only captions, ArtELingo adds another 0.79M annotations in Arabic and Chinese, plus 4.8K in Spanish to evaluate "cultural-transfer" performance. More than 51K artworks have 5 annotations or more in 3 languages. This diversity makes it possible to study similarities and differences across languages and cultures. Further, we investigate captioning tasks, and find diversity improves the performance of baseline models. ArtELingo is publicly available at https://www.artelingo.org/ with standard splits and baseline models. We hope our work will help ease future research on multilinguality and culturally-aware AI.