Annotation and classification of argumentative writing revisions

Abstract

This paper explores the annotation and classification of students' revision behaviors in argumentative writing. A sentence-level revision schema is proposed to capture why and how students make revisions. Based on the proposed schema, a small corpus of student essays and revisions was annotated. Studies show that manual annotation is reliable with the schema and the annotated information helpful for revision analysis. Furthermore, features and methods are explored for the automatic classification of revisions. Intrinsic evaluations demonstrate promising performance in high-level revision classification (surface vs. text-based). Extrinsic evaluations demonstrate that our method for automatic revision classification can be used to predict a writer's improvement.