A Triple Challenge: Students’ Identification, Interpretation, and Use of Individualized Automated Feedback in Learning to Write English as a Foreign Language

Abstract

The aim of this study was to investigate eighth-grade students’ assessment literacy and writing skills in English as a foreign language using an AI-based automated essay assessment tool (EAT). Data were gathered from a design-based research initiative where the EAT was designed, developed, and tested in naturalistic school settings. Fifty-six eighth-grade students wrote individual essays, for which they received automatic feedback. The feedback was discussed with their teachers and peers. Both the writing process and teacher and peer interactions were video recorded. The video data were analyzed using an interaction analysis. The improvements made on the essay based on the feedback logs registered by the EAT for each student’s writing trajectory and the different versions of the essay were examined using frequency analyses. The findings demonstrate that automated essay assessment might be useful for fostering students’ writing skills if teachers help students get started, identify errors, and share interpretations.