Empowering under-resourced communities with AI-illustrated picture books: An initiative in Palauan

Presented by Orlyn Joyce Esquivel at the Language Documentation and Archiving Conference, Berlin & Online, 4-6 Sept, 2024. Quality children’s literature, as an art form, combines carefully crafted language, expressive images, and sensitive design (Kiefer, 2008). Many examples of quality children’s literature are picture books. Through these books, children develop their understanding of the world and its people (Albers, 2009) and an understanding of their place within it (Driggs Wolfenbarger & Sipe, 2007). Particular features of picture books, such as illustrations, hold importance in illuminating texts and meaning. These visual cues not only serve to capture children’s attention but also aid in interpreting complex concepts and understanding narrative themes (Greenhoot et al., 2014). Therefore, producing quality illustrations for children’s literature is an enormous responsibility. However, high-quality picture book art is primarily associated with commercially produced books. Commercial publishers operate on a for-profit basis, prioritizing picture books that have the potential to generate revenue. Hence, commercially available picture books are often published in dominant languages, causing a scarcity of quality literature for smaller communities. Artificial intelligence (AI) has recently made its mark in the landscape of creating children’s literature. The once-labor-intensive task of illustrating a children’s book has now become significantly easier with the assistance of AI technology. Quality picture book art and illustrations, commonly found in commercially produced picture books, can now be generated through natural language descriptions, called prompts. This advancement from AI models offers transformative possibilities for creating and distributing quality picture books for under-resourced communities. Thus, this project showcases five bilingual picture books written in Palauan and English for preschool children. This includes translating existing English materials and adapting local Palauan stories and songs with the assistance of a native Palauan speaker. I used Midjourney, a generative AI program, to create appropriate and culturally relevant illustrations for the books. I also compared three leading AI models, DALL-E, Midjourney, and Leonardo Ai, to explain why I chose Midjourney for this project. Generally, the goal is to facilitate the preservation of Palauan language and culture and provide Palauan children with access to quality picture books. With high hopes, this project will serve as a model to motivate the creation of AI-powered picture books for Indigenous communities grappling with educational disparities and underrepresentation in literature.

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2024-09-04
DOI
https://doi.org/10.5281/zenodo.13889845
Primary Topic
Artificial Intelligence in Games
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Empowering under-resourced communities with AI-illustrated picture books: An initiative in Palauan

Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Games
article

Empowering under-resourced communities with AI-illustrated picture books: An initiative in Palauan

article en

Abstract

Presented by Orlyn Joyce Esquivel at the Language Documentation and Archiving Conference, Berlin & Online, 4-6 Sept, 2024. Quality children’s literature, as an art form, combines carefully crafted language, expressive images, and sensitive design (Kiefer, 2008). Many examples of quality children’s literature are picture books. Through these books, children develop their understanding of the world and its people (Albers, 2009) and an understanding of their place within it (Driggs Wolfenbarger & Sipe, 2007). Particular features of picture books, such as illustrations, hold importance in illuminating texts and meaning. These visual cues not only serve to capture children’s attention but also aid in interpreting complex concepts and understanding narrative themes (Greenhoot et al., 2014). Therefore, producing quality illustrations for children’s literature is an enormous responsibility. However, high-quality picture book art is primarily associated with commercially produced books. Commercial publishers operate on a for-profit basis, prioritizing picture books that have the potential to generate revenue. Hence, commercially available picture books are often published in dominant languages, causing a scarcity of quality literature for smaller communities. Artificial intelligence (AI) has recently made its mark in the landscape of creating children’s literature. The once-labor-intensive task of illustrating a children’s book has now become significantly easier with the assistance of AI technology. Quality picture book art and illustrations, commonly found in commercially produced picture books, can now be generated through natural language descriptions, called prompts. This advancement from AI models offers transformative possibilities for creating and distributing quality picture books for under-resourced communities. Thus, this project showcases five bilingual picture books written in Palauan and English for preschool children. This includes translating existing English materials and adapting local Palauan stories and songs with the assistance of a native Palauan speaker. I used Midjourney, a generative AI program, to create appropriate and culturally relevant illustrations for the books. I also compared three leading AI models, DALL-E, Midjourney, and Leonardo Ai, to explain why I chose Midjourney for this project. Generally, the goal is to facilitate the preservation of Palauan language and culture and provide Palauan children with access to quality picture books. With high hopes, this project will serve as a model to motivate the creation of AI-powered picture books for Indigenous communities grappling with educational disparities and underrepresentation in literature.

Zenodo (CERN European Organization for Nuclear Research)
Quality Education
Openalex Percentile: Top 65%
Artificial Intelligence in Games
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.