Predicting the CEFR level of learner writing with large language models and machine learning methods

Research Project

Project/Area Number	25K04353
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Multi-year Fund
Section	一般
Review Section	Basic Section 02100:Foreign language education-related
Research Institution	Rikkyo University
Principal Investigator	クーパークリストファー・ロバート立教大学, 外国語教育研究センター, 特任准教授 (90914002)
Co-Investigator(Kenkyū-buntansha)	投野由紀夫東京外国語大学, 大学院総合国際学研究院, 教授 (10211393)
Project Period (FY)	2025-04-01 – 2028-03-31
Project Status	Granted (Fiscal Year 2025)
Budget Amount *help	¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000) Fiscal Year 2027: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000) Fiscal Year 2026: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000) Fiscal Year 2025: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Keywords	corpus linguistics / machine learning / CEFR / learner writing / text classification
Outline of Research at the Start	A freely available tool will be developed that can accurately predict the writing ability level of learners of English as a Foreign Language based on the Common European Framework of Reference (CEFR). To achieve this goal, a large dataset of learner writing will be used in conjunction with large language models and machine learning methods. The results will be validated using other publicly available collections of learner writing. In addition CEFR level prediction will be done using commercial large language models (e.g. ChatGPT) for comparison.