A webcam-only automatic cheating detector achieved recall of 78.6%, precision of 84.6%, and accuracy of 83.3% in a MOOP experiment¶

Claim · All claims
Evidence · 1 study · quant-synthesis r? · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? In the MOOP framework experiment, the webcam-only ACD achieved recall 78.6%, precision 84.6%, and accuracy 83.3%, while the multi-modal ACD improved recall at the expense of precision and accuracy. → Malhotra 2026

Evidence¶

Malhotra 2026¶

Malhotra, M., & Chhabra, I. (2026). Ensuring academic integrity through automated online exam proctoring a decade long systematic review. Discover Education. https://doi.org/10.1007/s44217-026-01224-3

q2 · i? · quant-synthesis · r?

Experiment within a reviewed study (Li et al., described by the review) in a computer science exam scenario using Kinect cameras, an S2 eye-tracker, and EEG monitoring; the webcam-only ACD "achieved a recall of 78.6%, precision of 84.6%, and accuracy of 83.3%."

"The experiments show that the webcam-only version of ACD achieved a recall of 78.6%, precision of 84.6%, and accuracy of 83.3%. On the other hand, the multi-modal ACD, which includes more sophisticated sensors, displayed improvements in recall but at the expense of precision and overall accuracy."

Discussion¶

Related Claims¶

• Time delay and head pose variations relative to the screen were significant predictors of cheating, yielding 75.6% average detection accuracy — related
• Independent evaluation found commercial AI-text detectors neither sufficiently accurate nor sufficiently reliable for high-stakes use — related
• Eye-gaze-tracking-based proctoring systems report cheating-detection accuracies around 95–98% in their original studies — related
• Head-pose-estimation-based proctoring systems report widely varying accuracies, from 75.6% for cheating detection to 100% for yaw-angle estimation — related