ENA traced NLP-coded science ideas across an adaptive AI dialog
Journal of Science Education and Technology
A study of 196 eighth-grade students combined NLP-generated idea codes with ENA to represent how science explanations changed across two adaptive prompts. Higher knowledge-integration scores were associated with more connections among microscopic and mechanistic ideas, but the one-school design does not isolate a causal dialog effect.
Le résumé vérifié de l'article est actuellement disponible en anglais.
Lire le résumé vérifié