Learner-chatbot EFL writing interaction follows two dominant behavioural loops: a Revision Loop and a Chat Loop¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? After receiving chatbot feedback, learners diverge into revising their writing (42.6%) or entering dialogue with the chatbot (38.3%), forming distinct Revision and Chat Loops. → Steve Woollaston 2026

Evidence¶

Steve Woollaston 2026¶

Steve Woollaston, Brendan Flanagan, Yuko Toyokawa and Hiroaki Ogata. (2026). Penny: Transition Network Analysis of Learner-Chatbot Interactions in Scaffolded EFL Writing. Preprint, accepted at the 1st Workshop on Transition Network Analysis (TNA) at LAK '26. https://arxiv.org/abs/2607.14575 doi:10.48550/arxiv.2607.14575

q2 · i? · associational · r2

Transition Network Analysis of log data from 119 Japanese junior high EFL learners using Penny over four months. The network (10 nodes, 26 edges, density 0.29, reciprocity 0.31) showed "a distinct “Revision Loop” and “Chat Loop”"; after feedback, 42.6% revised and 38.3% moved to user_chat.

"The transition probabilities reveal a distinct “Revision Loop” and “Chat Loop” within the learning process."

Discussion¶

Related Claims¶

• Revision after chatbot feedback predominantly results in successful uptake, indicating effective error correction — related
• EFL proficiency significantly shapes chatbot interaction: high-proficiency learners over-engage in dialogue while low-proficiency learners over-rely on feedback requests — related
• Interactive dialogue with the AI tool, available only in some sites, promoted deeper engagement and student agency during revision — related
• Transition network analysis shows the chatbot's prompts and explanations structured the interaction while participants generated their own interpretations — related