Writing-to-Learn : evidence-based instructional practice that helps students construct knowledge across many disciplines.
But, instructors do not implement WTL in their courses due to time constraints and inability to provide students with personalized feedback.
⇒ Peer Review, which allows students to receive feedback on their writing and benefits as they act as reviewers
Labeling students’ peer review comments across courses for type of feedback provided
Training a machine learning model to automatically classify those comments, improving upon models reported in prior work
Creating a dashboard which takes students’ comments
Labeling the comments using the model
Allowing instructors to filter through their students’ comments based on how the model labels the comments
Writing-to-Learn (WTL) : writing as a way to help students construct knowledge
Peer Review Comments : contain rich data about students’ writing which could be useful for instructors
Natural language processing (NLP)
As training a model to classify writing requires humans to manually label writing, it is desirable to train models that are generalizable (lit review에서 나온 scheme 이용 : Problem/Solution, Praise, Verification/Summary)
Making Tier