Large language models for folktale type automation based on motifs: Cinderella case study

2025-10-21

AI Summary

This study addresses the challenge of large-scale, cross-lingual variant analysis in folk narrative typology. Methodologically, it proposes an automated motif identification and comparative framework leveraging large language models (LLMs) integrated with NLP techniques to perform fine-grained motif extraction from multilingual *Cinderella* texts; structural similarity modeling and visualization across hundreds of variants are achieved via clustering and dimensionality reduction. Its key contributions are twofold: (1) the first deep integration of LLMs into computational folklore analysis, overcoming bottlenecks of manual coding; and (2) construction of a cross-lingually aligned motif vector space, markedly improving thematic consistency detection and motif variation pattern recognition. Experimental evaluation demonstrates the framework’s effectiveness in motif identification accuracy, cross-lingual comparability, and interpretability of cultural divergence—establishing a scalable, digital-humanities–driven methodological paradigm for folk narrative studies.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Artificial intelligence approaches are being adapted to many research areas, including digital humanities. We built a methodology for large-scale analyses in folkloristics. Using machine learning and natural language processing, we automatically detected motifs in a large collection of Cinderella variants and analysed their similarities and differences with clustering and dimensionality reduction. The results show that large language models detect complex interactions in tales, enabling computational analysis of extensive text collections and facilitating cross-lingual comparisons.

Problem

• Automating folktale type classification using motif detection
• Analyzing similarities in Cinderella variants through computational methods
• Enabling cross-lingual comparisons of folktales with large language models

Innovation

• Using large language models for motif detection
• Applying clustering to analyze tale similarities
• Employing dimensionality reduction for cross-lingual comparisons