works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.CL2026

Accurate but Natural? Diagnosing Grammatical and Idiomatic Gaps in Japanese EFL Writing

Steve Woollaston, Brendan Flanagan, Hiroaki Ogata

Second language writing research distinguishes grammatical accuracy from native-like idiomaticity, yet automated writing evaluation often conflates these dimensions. This study int…

cs.CY2026

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

Steve Woollaston, Brendan Flanagan, Yuko Toyokawa +1

The paper studies how Japanese learners of English use an LLM-powered writing chatbot, analyzing interaction patterns with transition network analysis to reveal distinct revision a…

cs.CY2026

Agentic AI and Pedagogical Best Practice: The Tension Between Automation and Learning

Steve Woollaston, Brendan Flanagan, Isanka Wijerathne +1

Artificial intelligence in education is evolving from passive chatbots to proactive AI agents capable of initiation and goal-directed interactions. While offering opportunities for…

cs.CY2026

Question Type, Cognitive Load, and CEFR Alignment: Evaluating LLM-Generated EFL Grammar Drill Exercises

Steve Woollaston, Brendan Flanagan, Yuko Toyokawa +1

This study evaluates the pedagogical viability of LLM-generated English as a Foreign Language (EFL) learning content. Utilising log data from Japanese junior high school students p…

cs.AI2024

How Good is ChatGPT in Giving Adaptive Guidance Using Knowledge Graphs in E-Learning Environments?

Patrick Ocheja, Brendan Flanagan, Yiling Dai +1

E-learning environments are increasingly harnessing large language models (LLMs) like GPT-3.5 and GPT-4 for tailored educational support. This study introduces an approach that int…