Neural Cognitive Diagnosis for Empirical Q-Matrix

The growth of educational informatization has been aided by the constant updating and switching of application modes brought about by the continual development of a new generation of information technologies such as artificial intelligence, cloud computing, data mining, and mobile Internet. Cognitive diagnosis aims to assess students’ knowledge competency and offer a foundation for targeted instruction and teacher feedback. The neural cognitive diagnosis framework for the empirical Q-matrix is proposed in the research. The neural cognitive diagnosis framework for empirical Q-matrix introduces empirical Q-matrix, which to a certain extent reduces the subjectivity of artificial Q-matrix, to construct and select the most appropriate Q-matrix; accurate and interpretable diagnostic results are obtained by combining neural network and learning complex motion interaction function.