Modeling Students’ Ability to Recognize and Review Graded Answers that Require Immediate Attention

Abstract

Students utilize various resources to prepare for an examination, such as lecture materials, homework, or previous quizzes or tests. Reviewing graded tests allows students to develop their metacognitive skills. However, a lack of proper guidance, exacerbated by a lack of maturity, hinders fully realizing the benefits of learning from past mistakes. In this paper, we investigated students' reviewing strategies. We analyzed the clickstream data of students taking a Computer Science Education course. Using Hidden Markov models (HMMs), we modeled the reviewing behaviors of high-performing and lowperforming students. Our preliminary findings suggest that the two groups share some similar strategies but also have some that are particular to the group.