Tuned Models of Peer Assessment in MOOCs
This addresses the challenge of scaling accurate grading for open-ended assignments in massive online courses, which is incremental as it builds on existing peer assessment methods.
The paper tackled the problem of inaccurate peer grading in MOOCs by developing algorithms to estimate and correct grader biases and reliabilities, resulting in significant improvement in accuracy on a dataset of 63,199 peer grades from Coursera's HCI courses.
In massive open online courses (MOOCs), peer grading serves as a critical tool for scaling the grading of complex, open-ended assignments to courses with tens or hundreds of thousands of students. But despite promising initial trials, it does not always deliver accurate results compared to human experts. In this paper, we develop algorithms for estimating and correcting for grader biases and reliabilities, showing significant improvement in peer grading accuracy on real data with 63,199 peer grades from Coursera's HCI course offerings --- the largest peer grading networks analysed to date. We relate grader biases and reliabilities to other student factors such as student engagement, performance as well as commenting style. We also show that our model can lead to more intelligent assignment of graders to gradees.