Advancements in Automated Cheating Detection Systems for Online and In-Person Examinations: A Comprehensive Review of Methods, Technologies, and Effectiveness

Abstract

Authenticity of tests as a measurement tool has received a lot of attention within learning institutions due to emergences of online classes and remote test administration. Supervision and invigilation methods do not always suffice to deter students from cheating, and thus Academic Cheating Detection Systems (ACDETS) have been invented. This paper presents a critical analysis of the current approaches for identifying cheating in online and face-to-face examination systems. There are plenty of approaches, including behavioral approach, facial expressions tracking, gestures recognition, voice analysis, and video monitoring. CNN (Convolutional Neural Network) algorithms, RNN (Recurrent Neural Network) algorithms, and YOLO models, for instance, have shown great enhancements in both accuracy and scalability of detecting suspicious behaviors. The paper further compares the merits and demerits of these methods and also looks at the possibility of using them for real time detection, large setting for exams, and varied testing conditions. This paper is finalized by the evaluation of the practical applicability of the findings, limitations, and further research prospects concerning the monitoring of academic integrity.