论文标题
BKT-LSTM：知识追踪和学生绩效预测的高效学生建模
BKT-LSTM: Efficient Student Modeling for knowledge tracing and student performance prediction
论文作者
论文摘要
最近，我们看到在线教育平台的使用迅速上升。个性化的教育在未来的学习环境中至关重要。知识追踪（KT）是指对学生知识状态的检测，并预测未来的表现，因为他们的过去成果为智能辅导系统（ITS）提供了自适应解决方案。贝叶斯知识跟踪（BKT）是一种模型，可以用心理意义的参数捕获每种技能的精通水平，并广泛用于成功的辅导系统中。但是，它无法检测到跨技能的学习转移，因为每个技能模型都是独立学习的，并且显示出较低的学生绩效预测效率。尽管最近基于深神经网络的KT模型具有令人印象深刻的预测能力，但它具有价格。神经网络中成千上万的参数中的十个参数无法提供反映认知理论的心理意义的解释。在本文中，我们提出了一个有效的学生模型，称为BKT-LSTM。它包含三个有意义的组成部分：由BKT，\ textit {communition {community {commigent {commuction profile}评估的个人\ textit {技能掌握}（跨技能学习），由k-means群集和\ textit {问题难度}检测到。所有这些组件都通过利用LSTM的预测能力来考虑学生的未来绩效预测。 BKT-LSTM通过考虑这些有意义的功能而不是使用DKT中学生过去互动的二进制值来优于学生表现预测的最先进的学生模型。我们还对每个BKT-LSTM模型组件进行消融研究以检查其价值，并且每个组件在学生的表现预测中都有显着贡献。因此，它具有在现实世界教育系统中提供自适应和个性化教学的潜力。
Recently, we have seen a rapid rise in usage of online educational platforms. The personalized education became crucially important in future learning environments. Knowledge tracing (KT) refers to the detection of students' knowledge states and predict future performance given their past outcomes for providing adaptive solution to Intelligent Tutoring Systems (ITS). Bayesian Knowledge Tracing (BKT) is a model to capture mastery level of each skill with psychologically meaningful parameters and widely used in successful tutoring systems. However, it is unable to detect learning transfer across skills because each skill model is learned independently and shows lower efficiency in student performance prediction. While recent KT models based on deep neural networks shows impressive predictive power but it came with a price. Ten of thousands of parameters in neural networks are unable to provide psychologically meaningful interpretation that reflect to cognitive theory. In this paper, we proposed an efficient student model called BKT-LSTM. It contains three meaningful components: individual \textit{skill mastery} assessed by BKT, \textit{ability profile} (learning transfer across skills) detected by k-means clustering and \textit{problem difficulty}. All these components are taken into account in student's future performance prediction by leveraging predictive power of LSTM. BKT-LSTM outperforms state-of-the-art student models in student's performance prediction by considering these meaningful features instead of using binary values of student's past interaction in DKT. We also conduct ablation studies on each of BKT-LSTM model components to examine their value and each component shows significant contribution in student's performance prediction. Thus, it has potential for providing adaptive and personalized instruction in real-world educational systems.
