© 2019 IEEE. Many educational institutions enforce attendance policies, where students are expected to have their absences below a certain percentage in each class. Attendance records are collected to enforce such policies, but they are rarely utilized for anything else. In this paper, we investigate the value of analyzing the records pulled from student attendance systems. We apply a data mining technique, the market basket analysis, on student attendance data. The contribution of this analysis is the identification of student groups who share highly similar absence records. Such similarity may indicate that the students are missing classes due to peer pressure, rather than valid excuses. The presented method helps instructors and advisors discover this behavior, which is more efficient than relying on instructors, who may teach many classes. To minimize the number of false alarms, student groups are ranked based on their absence similarity. We tested our method by analyzing student attendance data for over two thousand students for one semester at a public higher education institution. The results were helpful in identifying students with miss classes due to their friends missing the classes.
- Educational data mining,
- Learning analytics,
- Mining student behavior
Available at: http://works.bepress.com/mohammed-hussain/9/