高级检索

    知识点相关性与遗忘程度融合的深度知识追踪模型

    Deep Knowledge Tracing Model with the Integration of Skills Relation and Forgetting Degree

    • 摘要: 知识追踪是对学习者知识水平建模的一种技术,根据学习者过去的学习交互预测其未来答题表现,这些交互代表了学习者回答一个习题序列的过程. 当前知识追踪方法在建模学习者遗忘行为时缺乏考虑知识点重复练习次数,并且少有模型考虑知识点相关性对答题预测的影响. 基于此,提出了一个融合知识点相关性和遗忘程度的深度知识追踪模型. 首先使用统计方法构建了一个关联矩阵,以捕获知识点之间的相关性. 其次,利用交互之间的时间间隔和学习者学习同一知识点的次数来计算知识点的遗忘程度,以更好地拟合学生的遗忘行为. 最后,将知识点相关性和遗忘程度整合到一个注意力模块中,以获得过去的每个交互对未来答题的影响,据此预测学习者的答题结果. 在真实的在线教育数据集algebra2005-2006和ASSISTment2012上的实验表明,相较于已有主流方法,所提模型取得了更好的预测结果.

       

      Abstract: Knowledge tracing is a pivotal technique for modeling students' knowledge level, typically relies on their past learning interactions to predict their future performance on exercises. These interactions represent a student's process of answering a sequence of questions. Current knowledge tracing methods ignore the number of times a skill has been practiced when modeling student’s forgetting behaviors. Also, few models consider the relation between skills and its influence on performance prediction. To address these questions, we propose a deep knowledge tracing model with the integration of skills relation and forgetting degree. Firstly, a relation matrix is constructed using statistical methods to capture the relation between skills. Secondly, the time intervals between interactions and the number of times a student practices the same skill are used to compute the forgetting degree of each skill for better modeling of students' forgetting behaviors. Finally, skills relation and forgetting degrees are integrated into an attention module to obtain the influence of each past interaction on future performance prediction. Based on new attention weights, students' performance on future exercises and kon can be predicted. Experiments on two real-world online education datasets, algebra2005-2006 and ASSISTment 2012, demonstrate that the proposed model achieves better prediction results compared to existing mainstream methods.

       

    /

    返回文章
    返回