Predicting Desirable Revisions of Evidence and Reasoning in Argumentative Writing

02/10/2023

∙

by   Tazin Afrin, et al.

∙

0

∙

share

We develop models to classify desirable evidence and desirable reasoning revisions in student argumentative writing. We explore two ways to improve classifier performance - using the essay context of the revision, and using the feedback students received before the revision. We perform both intrinsic and extrinsic evaluation for each of our models and report a qualitative analysis. Our results show that while a model using feedback information improves over a baseline model, models utilizing context - either alone or with feedback - are the most successful in identifying desirable revisions.