Annotating Student Talk in Text-based Classroom Discussions

TL;DR

This paper presents an annotation scheme for student talk in text-based classroom discussions, focusing on argumentation, specificity, and knowledge domain, which can predict discussion quality and aid educational NLP research.

Contribution

It introduces a novel annotation scheme for student talk that is reliable and predictive of discussion quality, advancing research in education and natural language processing.

Findings

Annotations are reliable and predictive of discussion quality

Scheme highlights opportunities for educational and NLP research

Provides a new framework for analyzing student talk

Abstract

Classroom discussions in English Language Arts have a positive effect on students' reading, writing and reasoning skills. Although prior work has largely focused on teacher talk and student-teacher interactions, we focus on three theoretically-motivated aspects of high-quality student talk: argumentation, specificity, and knowledge domain. We introduce an annotation scheme, then show that the scheme can be used to produce reliable annotations and that the annotations are predictive of discussion quality. We also highlight opportunities provided by our scheme for education and natural language processing research.