A Machine Learning Approach for the Simultaneous Detection of Preknowledge in Examinees and Items When Both Are Unknown

Pan and Wollack (PW) proposed a machine learning method to detect compromised items. We extend the work of PW to an approach detecting compromised items and examinees with item preknowledge simultaneously and draw on ideas in ensemble learning to relax several limitations in the work of PW. The suggested approach also provides a confidence score, which is based on an autoencoder to represent our confidence that the detection result truly corresponds to item preknowledge. Simulation studies indicate that the proposed approach performs well in the detection of item preknowledge, and the confidence score can provide helpful information for users.

Automated summary

This research extends the work of PW by proposing an approach to simultaneously detect compromised items and examinees with item preknowledge. It draws on ideas in ensemble learning to overcome limitations in PW's work. The suggested approach also provides a confidence score based on an autoencoder to indicate the reliability of the detection result. Simulation studies show that the proposed approach performs well in detecting item preknowledge and the confidence score can be useful for users.