Skip to main content

ETHNOS_APP

Home • Search • Journals • List 0

AI-Generated Tailor-Made Pedagogical Picture Books

How Close Are We

Bibliographic Data

ID22047009
AuthorsBranislav Bédi (0000-0001-7637-8737, Árni Magnússon Institute for Icelandic Studies), Hakeem Beedar (South Australia Pathology), Belinda Chiera (0000-0001-9274-0943, University of South Australia), Cathy Chua (0000-0002-5462-2441, South Australia Pathology), Stéphanie Geneix-Rabault (0000-0002-6516-9697, University of New Caledonia), Vanessa Kreusch (The University of Adelaide), Christèle Maizonniaux (0000-0003-2844-1820, Flinders University), Manny Rayner (South Australia Pathology, corresponding author), Sophie Rendina (0009-0004-8847-3394, South Australia Pathology), Emily Ryan-Cooper (South Australia Pathology), Vladyslav Sukhyi (Animal Production Research Centre), Ivana Vargova (Constantine the Philosopher University in Nitra), Ivana Horváthová (0000-0002-8388-7692, Constantine the Philosopher University in Nitra), Sarah Wright (0000-0002-8595-4529, South Australia Pathology), Chunlin Yao (0000-0001-6006-5031, Tianjin Chengjian University), Rina Zviel-Girshin (0000-0002-7926-4476, Ruppin Academic Center)
Year2025
Volume15
Issue12
Pages1704
Publication date2025-12-17
Open AccessYes
TypeARTICLE
VenueEducation Sciences (JOURNAL)
Journal identifiersISSN: 2227-7102 • E-ISSN: 2227-7102
PublisherMDPI AG (PUBLISHER • IT)
DOI10.3390/educsci15121704
OpenAlexW4417431735
LanguageEN
References cited21

Illustrated digital picture books are widely used for second-language reading and vocabulary growth. We ask how close current generative AI (GenAI) tools are to producing such books on demand for specific learners. Using the ChatGPT-based Learning And Reading (C-LARA) platform with GPT-5 for text/annotation and GPT-Image-1 for illustration, we ran three pilot studies. Study 1 used six AI-generated English books glossed into Chinese, French, and Ukrainian and evaluated them using page-level and whole-book Likert questionnaires completed by teachers and students. Study 2 created six English books targeted at low-intermediate East-Asian adults who had recently arrived in Adelaide and gathered student and teacher ratings. Study 3 piloted an individually tailored German mini-course for one anglophone learner, with judgements from the learner and two germanophone teachers. Images and Chinese glossing were consistently strong; French glossing was good but showed issues with gender agreement, register, and naturalness of phrasing; and Ukrainian glossing underperformed, with morphosyntax and idiom errors. Students rated tailored English texts positively, while teachers requested tighter briefs and curricular alignment. The German pilot was engaging and largely usable, with minor image-consistency and cultural-detail issues. We conclude that for well-supported language pairs (in particular, English–Chinese), the workflow is close to classroom/self-study usability, while other language pairs need improved multi-word expression handling and glossing. All resources are reproducible on the open-source platform. We adopt an interdisciplinary stance which combines aspects taken from computer science, linguistics, and language education

Computer-Assisted Instruction · German · Likert scale · Naturalness · Reading comprehension · Vocabulary · Vocabulary development · AI in Service Interactions · Artificial Intelligence in Healthcare and Education · Text Readability and Simplification

  • Multimedia learning

    Richard E Mayer•Advances in Research and Theory…•2002

  • Free access to multilingual digital books

    Open Access•Adriana G Bus, Kees Broekhof et al.•Frontiers in Education•2023

  • Digital Picture Books for Young Dual Language Learners

    Open Access•Katarzyna A Tunkiel, Katarzyna Tunkiel et al.•Frontiers in Education•2022

  • Does AI Simplification of Authentic Blog Texts Improve Reading Comprehension, Inferencing, and Anxiety? A One-Shot Intervention in Turkish EFL Context

    Open Access•Ferdi Çelık, Ceylan Yangın Ersanlı et al.•The International Review of…•2024

  • Digital Language Learning (DLL)

    Open Access•P Li, Yu-Ju Lan et al.•Bilingualism Language and Cognition•2022

  • How Did the Generative Artificial Intelligence‐Assisted Digital Multimodal Composing Process Facilitate the Production of Quality Digital Multimodal Compositions

    Open Access•Lianjiang Jiang, Chun Lai•TESOL Quarterly•2025

Highly citedNo

Tools

Open DOIOpen Access
Ethnos_APP • Open Source Project • MIT License • Frontend v2.0.0 • Privacy and Cookies • API Documentation: api.ethnos.app/docs • API Source Code: GitHub • DOI: 10.5281/zenodo.17049435 • Frontend Source Code: GitHub • DOI: 10.5281/zenodo.17050053 • cruz.rio.br • Expectantes Misericordiae