A Data Mining Approach for Detecting Collusion in Unproctored Online Exams

TL;DR

This paper presents a data mining approach to detect student collusion in unproctored online exams by analyzing event log data, identifying suspiciously similar exam patterns, and establishing criteria for suspicious cases.

Contribution

It introduces a novel method for detecting collusion in unproctored exams using event log analysis and compares findings with a proctored control group.

Findings

Identified groups of students with suspiciously similar exam patterns

Established a rule of thumb for evaluating suspicious similarity cases

Demonstrated effectiveness of data mining in collusion detection

Abstract

Due to the precautionary measures during the COVID-19 pandemic many universities offered unproctored take-home exams. We propose methods to detect potential collusion between students and apply our approach on event log data from take-home exams during the pandemic. We find groups of students with suspiciously similar exams. In addition, we compare our findings to a proctored control group. By this, we establish a rule of thumb for evaluating which cases are "outstandingly similar", i.e., suspicious cases.