Predicting Desirable Revisions of Evidence and Reasoning in Argumentative Writing

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.