[论文解读] EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction

Qi Liu, Zhenya Huang+5 more|arXiv (Cornell University)|Jun 7, 2019

Online Learning and Analytics参考文献 53被引用 52

一句话总结

本文提出了 EERNN 和 EKT 框架，通过同时利用练习内容和学生记录来预测学生表现，其中 EKT 提供跨多个概念的知识获取的可解释跟踪。

ABSTRACT

For offering proactive services to students in intelligent education, one of the fundamental tasks is predicting their performance (e.g., scores) on future exercises, where it is necessary to track each student's knowledge acquisition during her exercising activities. However, existing approaches can only exploit the exercising records of students, and the problem of extracting rich information existed in the exercise's materials (e.g., knowledge concepts, exercise content) to achieve both precise predictions of student performance and interpretable analysis of knowledge acquisition remains underexplored. In this paper, we present a holistic study of student performance prediction. To directly achieve the primary goal of prediction, we first propose a general Exercise-Enhanced Recurrent Neural Network (EERNN) framework by exploring both student's records and the exercise contents. In EERNN, we simply summarize each student's state into an integrated vector and trace it with a recurrent neural network, where we design a bidirectional LSTM to learn the encoding of each exercise's content. For making predictions, we propose two implementations under EERNN with different strategies, i.e., EERNNM with Markov property and EERNNA with Attention mechanism. Then, to explicitly track student's knowledge acquisition on multiple knowledge concepts, we extend EERNN to an explainable Exercise-aware Knowledge Tracing (EKT) by incorporating the knowledge concept effects, where the student's integrated state vector is extended to a knowledge state matrix. In EKT, we further develop a memory network for quantifying how much each exercise can affect the mastery of students on concepts during the exercising process. Finally, we conduct extensive experiments on large-scale real-world data. The results demonstrate the prediction effectiveness of two frameworks as well as the superior interpretability of EKT.

研究动机与目标

• 在跟踪知识获取的同时，推动对未来学生表现的准确预测。
• 将练习记录与练习的文本内容结合起来，以降低信息损失。
• 提供对多知识概念掌握程度的可解释跟踪。
• 通过练习内容和概念相关性来应对冷启动场景。
• 提供两种预测策略并扩展到可解释的知识追踪框架。

提出的方法

• 提出 EERNN：使用双向 LSTM 编码练习内容，并用将练习嵌入和回答整合的 RNN/LSTM 来建模学生状态。
• 实现两种 EERNN 预测策略：带马尔可夫性质的 EERNNM，以及对历史状态使用注意力机制的 EERNNA。
• 通过引入表示对 K 个知识概念熟练度的知识状态矩阵，将 EERNN 扩展为 EKT。
• 引入带记忆网络的知识嵌入模块，用于量化每道练习对每个知识概念的影响。
• 通过基于概念的输入来条件化的逐概念 LSTM 更新概念特定的知识状态。
• 在 EKT 框架内提供 EKTM（马尔可夫）和 EKTA（注意力）两种预测变体。

实验结果

研究问题

• RQ1 如何将练习内容有效地纳入知识追踪，以提高对未来表现的预测？
• RQ2 通过利用练习内容和概念相关性，预测是否能在冷启动场景中仍然有效？
• RQ3 对多种知识概念的显式掌握跟踪是否在不牺牲准确性的前提下提高了可解释性？
• RQ4 对历史练习的注意力（注意力机制）对预测未来表现有何影响？
• RQ5 提出的基于记忆的知识嵌入如何量化练习在概念之间的影响？

主要发现

• EERNN 和 EKT 框架在预测未来练习中的学生表现方面效果显著。
• EKT 通过对明确知识概念的掌握跟踪提供更高的可解释性。
• 基于注意力的 EERNNA 通过聚焦相关的历史状态改进预测。
• 知识嵌入捕捉概念之间的相关性，并帮助应对冷启动情景。
• 在大规模实际数据上的实验表明在一般情形和冷启动情景下均具有效性。