Context Matters: Advancing Knowledge Tracing in Online Learning with Enhanced Attention Mechanisms

Online learning platforms are widely used in the field of education and are popular for their ability to personalize learning plans based on students' individual needs and learning history. Knowledge tracking is an important task in the field of education, which aims to monitor students' learning progress and knowledge mastery. Traditional knowledge tracking methods mainly track students' knowledge state based on individual historical information, but often ignore the contextual information in the learning process of students, that is, the impact of recent similar learning experiences on the prediction accuracy of students' answers. Therefore, we propose enhanced knowledge tracing for online learning based on attention mechanisms, which can effectively use attention mechanisms to improve the performance of knowledge tracing models. First, we introduce parallel attention mechanism that adjusts its attention to different contextual information to better capture the impact of the latest relevant practices. Secondly, considering the influence of different factors can evaluate students' knowledge status more comprehensively and reduce the bias of single factor. The effectiveness of our proposed method is demonstrated by experiments on four real data sets, and the experimental results show that our method has the best performance.