Language Learning

Penny: Transition Network Analysis of Learner-Chatbot Interactions in Scaffolded EFL Writing

arXiv cs.CL 6 hours ago

Researchers analyzed over 4,500 writing sessions with Penny, an LLM-powered chatbot designed to provide feedback on English writing by Japanese EFL learners. The study found that learners follow two main interaction patterns: a Revision Loop where feedback leads to error correction, and a Chat Loop involving sustained dialogue, with high-proficiency learners engaging in more open negotiation while low-proficiency learners rely more on repetitive corrections. The results suggest chatbot design should be differentiated by proficiency level to promote deeper cognitive engagement rather than focusing solely on error correction.

AI Behavior & Psychology AI Dialogue Systems AI Education Language Learning

UzWordnet and Generative AI for Learning Uzbek by Game Playing

arXiv cs.CL 6 hours ago

Researchers developed an educational system that uses generative AI and game-playing to teach Uzbek language learners, integrating UzWordnet and Uzbek dictionary resources. The system includes four educational games designed to support language learning. The approach simultaneously improves UzWordnet as learners play the games.

AI Education Game-Based Learning Generative AI Language Learning

Friday, 17 July 2026

Penny: Transition Network Analysis of Learner-Chatbot Interactions in Scaffolded EFL Writing

UzWordnet and Generative AI for Learning Uzbek by Game Playing