Prediction of Grades for Reviewing with Automated Peer-review and Reputation Metrics

Peer review is an effective and useful method for improving students’ learning through review by student peers. Peer review has been used in classes for several decades. To ensure the success of peer review, research challenges such as the quality of peer review must be addressed. It is challenging to identify how good the reviewer is. We develop a prediction model to assess students’ reviewing capability. We investigate several important factors that influence students’ reviewing capability, which corresponds to instructor-assigned grades for reviewing. We use machine learning techniques algorithms to build models for grade prediction for reviewing. Our models are based on the several metrics such as the reviewer assigning different scores to different rubric items and automated metrics to assess the textual feedback given by the reviewers. To improve the models, we also use reputation score of students’ as reviewers. We present results of experiments to show the effectiveness of the models.