FKA-DKT:Deep Knowledge Tracing Model Based on the Fusion of Knowledge and Ability
Knowledge tracing(KT)is an important research problem in intelligent education,which predicts students'future answering behaviors by analyzing their historical interactions.Existing mainstream KT models only model students based on their knowledge mastery,neglecting the role of students'personal abilities in answering questions.Therefore,this paper proposes a deep knowledge tracing model(FKA-DKT)that integrates both knowledge and ability.First,we use the DKT model to construct a Knowledge-based Answer Prediction Network(KAPN),which predicts student answer correctness at the knowledge level.Then,we propose an Ability-based Answer Prediction Network(AAPN)to model students'abilities and predict answer correctness at the ability level.Finally,we linearly combine the predictions from KAPN and AAPN to integrate both knowledge and ability information for answer prediction.Experimental results on four publicly available datasets show that compared to existing mainstream methods,FKA-DKT achieves significant performance improvements in terms of the AUC metric.
万方数据
维普
