[1]周铖,郝国生,张谢华*,等.基于知识追踪和知识网络的学生成绩预测[J].计算机技术与发展,2024,34(08):202-208.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0164]
　ZHOU Cheng,HAO Guo-sheng,ZHANG Xie-hua*,et al.Predicting Student Performance Based on Knowledge Tracking and Knowledge Networks[J].,2024,34(08):202-208.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0164]
点击复制

基于知识追踪和知识网络的学生成绩预测

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年08期
页码:
202-208
栏目:
新型计算应用系统
出版日期:
2024-08-10

文章信息/Info

Title:
Predicting Student Performance Based on Knowledge Tracking and Knowledge Networks
文章编号:
1673-629X(2024)08-0202-07
作者:
周铖1; 郝国生1; 2; 张谢华1*; 杨晓菡1; 祝义1
1. 江苏师范大学 计算机科学与技术学院,江苏 徐州 221116; 2. 江苏思维驱动智能研究院有限公司,江苏 徐州 221000
Author(s):
ZHOU Cheng1; HAO Guo-sheng1; 2; ZHANG Xie-hua1*; YANG Xiao-han1; ZHU Yi1
1. School of Computer Science and Technology,Jiangsu Normal University,Xuzhou 221116,China; 2. Jiangsu Wisdom-driven Research Institute Co. ,Ltd. ,Xuzhou 221000,China
关键词:
知识追踪; 知识网络; 成绩预测; 注意力机制; 长短期记忆网络
Keywords:
knowledge tracking; knowledge networks; performance prediction; attention mechanism; long short-term memory (LSTM)
分类号:
TP18
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0164
摘要:
随着教育事业和数字技术的蓬勃发展,高校内大量学生学习数据开始以电子形式进行存储。 预测学生在未来学习中的表现(如成绩)成为一个重要课题。 在现有的学生成绩预测研究中,大多数忽略了学生历史习题之间隐含的关联性。 因此,该文提出了基于知识追踪和知识网络的学生成绩预测方法,其主要思想是融合知识追踪和习题对应知识点的知识网络实现成绩预测。 该方法将每个学生所做习题对应的知识点以及前驱知识点组成的知识网络作为输入之一,并在知识网络中标注出掌握程度大于给定阈值的知识点;结合 LSTM 神经网络,通过学生学习记录融合注意力机制来追踪学生知识水平,最终预测学生在未来做题中的表现。 在公开数据集上的实验结果表明,该模型在 Assistment2009 数据集上较DKT、DKT+、DKVMN、SAKT、MFKT、MSKT 分别提高了 2. 3% ,2. 2% ,3. 3% ,3. 4% ,0. 41% ,2. 0% ,在 Assistment2015 数 据集上分别提高了 9. 0% ,9. 4% ,9. 7% ,9. 3% ,8. 1% ,8. 5% ,具有较好的模型精度。
Abstract:
With the boom in education and digital technology, large amounts of student learning data are beginning to be stored in electronic form within universities. Predicting student performance (e. g. , grades) in future studies has become an important topic. In reported research on student performance prediction,most of them overlook the implicit correlation among students' historical exercises. Therefore,we propose a method to predict student performance based on knowledge networks and knowledge tracking. The main idea is to integrate the knowledge tracking and the knowledge network formed by the association between knowledge points of exercise. The pro-posed method takes the knowledge network composed of exercise-specific knowledge points and their precursor knowledge points as one of the inputs and masks the knowledge points with mastery level greater than a given threshold in the knowledge network. Combined with LSTM,students' knowledge level is tracked through the integration of learning records and attention mechanisms,ultimately predicting students' performance in future problem-solving. The experimental results on public datasets show that the model proposed improves by 2. 3% ,2. 2% ,3. 3% ,3. 4% ,0. 41% and 2. 0% on the Assistment2009 dataset,and by 9. 0% ,9. 4% ,9. 7% ,9. 3% ,8. 1% and 8. 5% on the Assistment2015 dataset,respectively,compared to DKT,DKT+,DKVMN,SAKT,MFKT and MSKT,has better model accuracy.

相似文献/References:

[1]孙名松 周三山 刘杰.分布式后缀树在P2P搜索中的应用[J].计算机技术与发展,2011,(03):31.
　SUN Ming-song,ZHOU San-shan,LIU Jie.Distributed Suffix Tree Overlay for Peer-to-Peer Search[J].,2011,(08):31.
[2]王有远,周声灵.基于本体的产品创新设计知识网络研究[J].计算机技术与发展,2018,28(01):195.[doi:10.3969/ j. issn.1673-629X.2018.01.042]
　WANG You-yuan,ZHOU Sheng-ling.Research on Knowledge Network of Product InnovationDesign Based on Ontology[J].,2018,28(08):195.[doi:10.3969/ j. issn.1673-629X.2018.01.042]
[3]王 斌,盛宇轩,冀星昀.DKTwMF:一种融合多特征的知识追踪模型[J].计算机技术与发展,2021,31(07):35.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 006]
　WANG Bin,SHENG Yu-xuan,JI Xing-yun.DKTwMF:A Deep Knowledge Tracing Model with Multiple Features[J].,2021,31(08):35.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 006]
[4]盖素丽,檀改芳,唐 松,等.面向科技服务的专家推荐模型研究[J].计算机技术与发展,2022,32(10):21.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 004]
　GE Su-li,TAN Gai-fang,TANG Song,et al.Expert Recommendation Model for Technology Services[J].,2022,32(08):21.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 004]

更新日期/Last Update: 2024-08-10