A Concept Interaction-Based Cognitive Diagnosis Deep Model
ZHANG Suojuan;YU Xiaohan;CHEN Enhong;SHEN Shuanghong;ZHENG Yu;HUANG Song;College of Command and Control Engineering, Army Engineer-ing University of PLA;Anhui Province Key Laboratory of Big Data Analysis and Ap-plication, School of Computer Science and Technology, Uni-versity of Science and Technology of China;
Cognitive diagnosis is an intelligent assessment technique of mining learners′ cognitive state based on learning data. Concepts in learning tasks are regarded as equally important by most cognitive diagnosis deep model. Without the consideration of the interaction between concepts, diagnosis accuracy is affected and interpretability is insufficient. To solve the problems, a concept interaction-based cognitive diagnosis deep model is proposed to realize the unified representation of students′ cognitive state and concept weights. In the meanwhile, an algorithm of ideal response calculation based on the Choquet integral is implemented. Finally, a deep neural network based on fuzzy measures is proposed to predict learners′ response performance. Experiments show that the proposed model holds advantages in prediction results and the explanation at the concept interaction level provided for prediction results.
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.