基于知识点扩增网络的薄弱认知诊断

Diagnosis of weak cognition based on concept-augmented network

针对学生在认知诊断过程中暴露出的问题,提出一种基于知识点扩增的薄弱认知诊断方法。利用异构网络对学生与习题之间的交互信息建模,并通过知识点扩增构建知识点扩增网络,以模拟学生、习题及知识点之间的交互关系。采用TF-IDF模型对链接关系进行加权来区分交互关系的重要性。在两个真实数据集上大量的实验,结果表明,所提方法的准确率提升了5.55%。

Diagnosis method of weak cognition based on knowledge concept augmentation is proposed to address the problems of students revealed in the diagnosis process of cognition.It models the interaction information between students and exercises by using heterogeneous networks,and constructs a concept-augmentation network by knowledge concept augmentation to model the interaction relationships among students,exercises and knowledge concepts.The TF-IDF model is used to weight the link relationships to distinguish the importance of the interactions.Extensive experiments are conducted on two real datasets,and the results show that the accuracy of the proposed method is improved by 5.55%.