Automation of cheating detection in knowledge tests: a new challenge for research

Remote online assessment of knowledge has been increasing in recent years and has accelerated with the current COVID-19 pandemic situation. The ability to conduct tests virtually using technology offers excellent flexibility and provides opportunities to candidates that were impossible otherwise. However, it can also carry some problems, including fraudulent means to answer questions, leading to biased results and unfair decisions. This phenomenon may significantly impact results in exams and lead to the certification of professionals who are not qualified to practice in the labor market. Therefore, it is essential to inhibit, mitigate, and perhaps even extinguish cheating, ensuring a fair result. Advanced computing, namely machine learning, has become more accessible and provide ways to apply advanced statistical tools to detect cheating in online tests. In real-time, the automation of this process is still in its infancy but is ever more pressing to develop.
To attain this objective, we have established the following tasks:
1. A systematic review of statistical cheating detection methods (ICVS).
2. Characterization of students’ and evaluators’ perspectives concerning cheating (ICVS).
3. Module validation in a documented cheating case (ICVS).
4. Development of a computer cheating detection module (iCognitus).

Funding Agency

Project Reference

Project Members

Main Project Outcomes

S. Queirós, “Right ventricular segmentation in multi-view cardiac MRI using a unified U-net model”, in E. Puyol Antón et al. (eds) Statistical Atlases and Computational Models of the Heart. Multi-Disease, Multi-View, and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge. STACOM 2021. Lecture Notes in Computer Science, vol 13131, pp. 287-295, Springer, Cham, 2022.

“Best Paper Award in the M&Ms-2 Challenge”, by M&Ms2 Challenge organizers and the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society.

Main Project Outcomes

Outputs: A systematic review on the use of statistical method for cheating detection is in preparation.