Analysis of Students' Online Interactions in the Covid Era from the Perspective of Anomaly Detection.

During the pandemic, most of the teaching has been done online. The lack of face-to-face interaction has many undesirable effects, including students being less focused, not receiving feedback on how they are approaching the current topic/task, and an increased risk of cheating. It is expected that those students with similarly graded assignments/exams would have similar interactions during online teaching sessions. The opposite is an anomaly, for better or worse. It is possible to find out if assignments/exams are legitimate by using anti-plagiarism tools or by carefully examining submissions, but it is time-consuming and only protects against one type of fraud. In this paper, we propose to apply anomaly detection techniques to the students' interactions to reduce the number of assignments/exams that need to be checked against fraud.