A Machine Learning Approach for the Simultaneous Detection of Preknowledge in Examinees and Items When Both Are Unknown. Issue 1 (24th February 2023)

• Record Type: Journal Article
• Authors: Pan, Yiqin; Wollack, James A.
• Is Part Of: Educational measurement. Volume 42:Issue 1(2023)
• Page Start: 76
• Page End: 98
• Publication Date: 2023-02-24
• Subjects: computer based testing -- machine learning -- test security; Educational tests and measurements -- Periodicals; Educational tests and measurements -- United States -- Periodicals; 371.262
• DOI: 10.1111/emip.12543
• Languages: English
• ISSNs: 0731-1745

Abstract

Abstract: 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.