Model separates skill and emotion to improve student learning predictions
Ability-Residual Decoupled Modeling for Affective Cognitive Diagnosis
Artificial Intelligence
Summary
Students’ answers depend not just on their knowledge but also on emotions like engagement and fatigue. Existing models often mix these effects, which can confuse which factors really influence performance. The authors propose a new method that separates stable skill-related effects from emotional influences, allowing for clearer understanding and better predictions. Their tests on multiple student datasets show improvements in accuracy and more precise recognition of emotional states.
What this means in practice
- •For educational software developers: Build smarter student assessment tools that distinguish knowledge from emotion-driven errors for more precise feedback.
- •For learning analytics teams: Improve accuracy in interpreting student response data by separating cognitive skill from emotional state effects in educational data analysis.
Authors
Boyuan Zhao, Meng Ye
Abstract
Cognitive diagnosis infers students' concept mastery from response logs. However, students' responses are not determined by mastery alone: non-cognitive factors such as emotion, engagement, and fatigue can also affect performance. Affective cognitive diagnosis therefore extends conventional cognitive diagnosis by incorporating affective states. Existing methods often assume that the cognitive diagnosis backbone has already explained ability, item, and concept effects, so the remaining errors can be attributed mainly to affect. We argue that this assumption can be insufficient in real educational data: item calibration bias, systematic concept bias, personalized student-concept deviations, and latent student-item matching can form stable cognitive residuals. Without an explicit modeling pathway, these residuals may leak into affective representations, producing affect contamination. To address this problem, we propose an ability-residual decoupled framework for affective cognitive diagnosis. The model first captures unmodeled cognitive residuals through student, item, concept, student-concept, and low-rank student-item components, and then uses an affective module to modulate guess/slip effects. A Q-matrix-constrained concept residual attention mechanism adaptively aggregates only item-relevant concept residuals. Experiments on ASSIST2017, ASSIST2012, ASSIST2009, and Junyi with six cognitive diagnosis backbones show response-prediction gains across the reported comparisons and generally improved affect alignment when affect labels are available. Ablation studies, leakage probes, principal component analysis visualization, long-tail analysis, and case studies further indicate that ability residuals absorb stable cognitive bias, reduce cognitive contamination in the affective branch, and enhance the robustness and predictive accuracy of cognitive diagnosis models.