Lehr- und Forschungseinheit für Datenbanksysteme
print


Breadcrumb Navigation


Content

Accepted Paper at ICPM 2023

Process Mining Techniques for Collusion Detection in Online Exams

16.10.2023

Authors

Andrea Maldonado, Ludwig Zellner, Sven Strickroth, and Thomas Seidl


icpm_logo2nd International Workshop “Education meets Process Mining" (EduPM 2023) organized with the 5th International Conference on Process Mining (ICPM 2023)

23-27 October, 2023, Rome, Italy

 

Abstract

Honesty and fairness are essential. As many skills, practicing those values starts in the classroom. Whether students are examined online or on-site, only testing their knowledge righteously, educators can assess their skills and room for improvement. As online exams increase, we are provided with more suitable data for analysis. Process mining methods as anomaly detection and trace clustering techniques have been used to identify dishonest behavior in other fields, as e.g. fraud detection. In this paper, we investigate collusion detection in online exams as a process mining task. We explore trace ordering for anomaly detection (TOAD) as well as hierarchical agglomerative trace clustering (HATC).
Promising preliminary results exemplify, how process mining techniques empower teachers in their decision making, while via flexible configuration of parameters, leaves the last word to them.