Predicting CEFR levels in learners of English: The use of microsystem criterial features in a machine learning approach. Issue 2 (10th May 2022)

• Record Type: Journal Article
• Authors: Gaillat, Thomas; Simpkin, Andrew; Ballier, Nicolas; Stearns, Bernardo; Sousa, Annanda; Bouyé, Manon; Zarrouk, Manel
• Is Part Of: ReCALL. Volume 34:Issue 2(2022)
• Page Start: 130
• Page End: 146
• Publication Date: 2022-05-10
• Subjects: microsystem -- criterial features -- supervised learning -- language functions -- automatic essay scoring -- linguistic complexity; Education -- Great Britain -- Periodicals; Languages, modern -- Periodicals; Language and languages -- Computer-assisted instruction -- Periodicals; Language and languages -- Study and teaching -- Europe -- Periodicals; 418.00785
• DOI: 10.1017/S095834402100029X
• Languages: English
• ISSNs: 0958-3440

Abstract

Abstract: This paper focuses on automatically assessing language proficiency levels according to linguistic complexity in learner English. We implement a supervised learning approach as part of an automatic essay scoring system. The objective is to uncover Common European Framework of Reference for Languages (CEFR) criterial features in writings by learners of English as a foreign language. Our method relies on the concept of microsystems with features related to learner-specific linguistic systems in which several forms operate paradigmatically. Results on internal data show that different microsystems help classify writings from A1 to C2 levels (82% balanced accuracy). Overall results on external data show that a combination of lexical, syntactic, cohesive and accuracy features yields the most efficient classification across several corpora (59.2% balanced accuracy).