Can Students Produce Effective Training Data to Improve Formative Feedback?
Yulin Zhang, Edward F. Gehringer · 2021 IEEE Frontiers in Education Conference (FIE) · 2021
This full research paper shows how machine learning can improve peer assessment by giving students advice on how to write better quality reviews. We trained a model that gives automated feedback by using labeled data produced by students over a period of several semesters. To improve the accuracy of the model, we are working to incorporate active learning (in the machine-learning sense) to direct students to produce training data for situations where the model has the most difficulty making predictions. With the active-learning approach, we expect students to have to do less labeling, so that they can be more attentive and produce more accurate labels. Our results revealed that we are able to cut the amount of labeling effort by half, without loss of reliable training data.