S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking Assessment

2025-05-14

AI Summary

Traditional creativity assessment relies on time-consuming, subjective, and linguistically/culturally bounded human scoring, limiting scalability and cross-cultural applicability. This paper introduces the first automated, multilingual framework for assessing divergent thinking (DT), centered on semantic distance—a language-agnostic core metric—computed via multilingual embedding models (e.g., mBERT, XLM-R) to quantify semantic dissimilarity between word pairs, integrated with standardized scoring protocols. Validated across 11 languages—including Japanese (employing its three-script system)—the framework demonstrates strong cross-linguistic consistency, as well as convergent and discriminant validity. It is publicly accessible online at no cost. The framework significantly enhances fairness, inclusivity, reproducibility, and scalability of DT assessment, establishing a robust, open-source infrastructure for cross-cultural creativity research.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Humans and AI: AI for Accessibility

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

This paper introduces S-DAT (Synthetic-Divergent Association Task), a scalable, multilingual framework for automated assessment of divergent thinking (DT) -a core component of human creativity. Traditional creativity assessments are often labor-intensive, language-specific, and reliant on subjective human ratings, limiting their scalability and cross-cultural applicability. In contrast, S-DAT leverages large language models and advanced multilingual embeddings to compute semantic distance -- a language-agnostic proxy for DT. We evaluate S-DAT across eleven diverse languages, including English, Spanish, German, Russian, Hindi, and Japanese (Kanji, Hiragana, Katakana), demonstrating robust and consistent scoring across linguistic contexts. Unlike prior DAT approaches, the S-DAT shows convergent validity with other DT measures and correct discriminant validity with convergent thinking. This cross-linguistic flexibility allows for more inclusive, global-scale creativity research, addressing key limitations of earlier approaches. S-DAT provides a powerful tool for fairer, more comprehensive evaluation of cognitive flexibility in diverse populations and can be freely assessed online: https://sdat.iol.zib.de/.

Problem

• Automates multilingual divergent thinking assessment using GenAI
• Overcomes labor-intensive, language-specific traditional creativity evaluations
• Ensures cross-linguistic validity and scalability in creativity research

Innovation

• Leverages large language models for semantic distance
• Uses multilingual embeddings for cross-linguistic flexibility
• Automates divergent thinking assessment globally