知识追踪研究进展  

Research Advances in Knowledge Tracing

作　　者：陈之彧 单志龙[1,2] CHEN Zhi-yu;SHAN Zhi-long(School of Computer Science,South China Normal University,Guangzhou 510631,China;School of Network Education,South China Normal University,Guangzhou 510631,China)

机构地区：[1]华南师范大学计算机学院,广州510631 [2]华南师范大学网络教育学院,广州510631

出　　处：《计算机科学》2022年第10期83-95,共13页Computer Science

基　　金：国家自然科学基金(62192711);广东省自然科学基金(2314050004664)。

摘　　要：教育数据挖掘是计算机科学、统计学与教育学的交叉学科,主要通过计算机科学与统计学的理论和技术处理教育研究与教学实践的问题,比如在获得最大学习增益的情况下尽可能降低学生的学习成本和教师的教育成本。迅速发展的计算机辅助教育环境和在线教育平台产生了丰富的数据,当然也带来了挑战,无法针对性地为学生提供特定需求的资源。知识追踪是智能辅导教育领域对学生进行教学资源推荐和学习路径诊断的个性化方法,随着时间的推移,对学生的知识状态进行建模,从而根据学生的历史响应序列,预测学生未来的表现。重点从具有可解释性的训练过程、具备高精度的预测结果两方面对知识追踪进行相关文献的分析,并且介绍了该领域常见的数据集、评价指标和应用。最后,对知识追踪领域的挑战进行了展望。Educational data mining is an interdisciplinary subject of computer science, statistics and pedagogy, and it mainly deals with the problems of educational research and teaching practice through the theory and technology of computer science and statistics.For example, it can reduce the learning cost of students and the educational cost of teachers as much as possible under the condition of obtaining the maximum learning gain.The rapid development of computer-assisted education environments and online education platforms has generated a wealth of data, which has also posed a major challenge, of course, but it cannot provide resources for students’ specific needs.Knowledge tracing is an individual method for recommending teaching resources and diagnosing learning paths in the field of intelligent tutoring education.With the time going on, students’ knowledge states can be mo-deled to predict their future performance based on their historical response sequences.This paper focuses on the analysis of relevant literature from two aspects: knowledge tracing model on training process with interpretability, prediction results with high precision, and then introduces the public datasets, evaluation metrics and applications in this field.Finally, the challenges of knowledge tracing are prospected.

关 键 词：在线教育 知识追踪 可解释性 高精度 

分 类 号：TP391.6[自动化与计算机技术—计算机应用技术]