Answers are grounded in this paper and cite their sources.
Auto-graders could be useful in MOOCs. While they are useful for closed-ended questions, there is still ongoing re-search on auto-graders for open-ended questions. In the software design patterns course, students were often asked to explain how the patterns are implemented in their programs and manual grading such assessments could be time-consuming. We plan to develop an auto-grader for explanations of software design pat-terns. It ranks the submissions based on their comprehensiveness and then assigns quality marks to them. For our initial study, we present the ranking method. Our evaluation of 310 submissions shows that the ranking method is satisfactory with around 55 % top-K precision.
No takes yet. Share an insight, caveat, or question.
Karnalim et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: