Interpretable neuro-cognitive diagnostic approach incorporating multidimensional features

Cognitive diagnostics is a pivotal area within educational data mining, focusing on deciphering students’ cognitive status via their academic performance. Traditionally, cognitive diagnostic models (CDMs) have evolved from manually designed probabilistic graphical models to sophisticated automated learning models employing neural networks. Despite their enhanced fitting capabilities, contemporary neuro-cognitive diagnostic models frequently overlook critical process information from students and suffer from reduced interpretability. To address these limitations, this paper introduces a neuro-cognitive diagnostic model that integrates multidimensional features (MFNCD) by incorporating students’ response time as process information. This approach facilitates the simultaneous modeling of students’ response accuracy and response speed using neural networks, thereby enhancing both the fitting capability and precision of the method. Furthermore, a multi-channel attention mechanism is employed to effectively capture the complex interactions between students and exercise characteristics, simulating the process of students answering questions and thereby improving the model's interpretability. Validated on four diverse datasets, MFNCD model demonstrates superior accuracy compared to other state-of-the-art (SOAT) baseline models. Additionally, our experiments confirm significant correlations between cognitive attributes, revealing interesting educational patterns, such as a positive correlation between speed and ability, and between ability and accuracy. These findings provide deeper insights into learning patterns that incorporate multidimensional features and suggest potential pathways for targeted educational interventions.