Transformation of Classic English and American Literature into Children's Literature Using Artificial Intelligence <Focusing on Text and Image Generation Models>
This study aims to explore the possibility of transforming classic English and American literature into children's literature using artificial intelligence technology.Traditional classic literary works often contain deep themes and complex narratives, making them difficult for children to understand.This study investigates methods for converting Classic English and American literature into a child-friendly writing style using generative AI technology and creating illustrations to complement the text visually.Language models such as ChatGPT, Claude, and Gemini were utilized for text generation, while image generation was conducted using Midjourney, DALL-E, and KlingAI.Experimental results showed that the Claude 3.5 Sonnet model generated the most natural and childfriendly sentences, and the 1-shot prompting method was identified as the most effective approach in the transformation process.Regarding image generation, DALL-E was selected as the most suitable model for producing illustrations appropriate for young readers.This study suggests the potential of AI technology to innovate literary education and proposes a new approach to providing children with a richer literary experience.Additionally, through expert-driven qualitative evaluation and a multi-layered experimental design, the study offers a detailed analysis of the characteristics and distinctions among various generative AI models.These findings provide foundational data for future applications and strategic uses of AI in children's content production.
Authors
- Jeongmin Ahn (ORCID: https://orcid.org/0000-0002-9041-6100)
- Y.H. Lim
Publication Details
- Journal
- Asia-pacific Journal of Convergent Research Interchange
- Published
- 2025-05-29
- DOI
- https://doi.org/10.47116/apjcri.2025.05.02
- Citations
- 1
- Primary Topic
- Diverse Approaches in Healthcare and Education Studies
- Type
- article
- Field-Weighted Citation Impact
- 1.88