计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (3): 197-205.doi: 10.11896/jsjkx.240700151

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于试题-知识点异构图和多特征融合的知识追踪模型

解培中, 李冠进, 李汀   

  1. 南京邮电大学通信与信息工程学院 南京 210003
  • 收稿日期:2024-07-23 修回日期:2024-10-18 出版日期:2025-03-15 发布日期:2025-03-07
  • 通讯作者: 解培中(cas@njupt.edu.cn)
  • 基金资助:
    国家自然科学基金(62277032)

Knowledge Tracing Model Based on Exercise-Knowledge Point Heterogeneous Graph andMulti-feature Fusion

XIE Peizhong, LI Guanjin, LI Ting   

  1. School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
  • Received:2024-07-23 Revised:2024-10-18 Online:2025-03-15 Published:2025-03-07
  • About author:XIE Peizhong,born in 1968,Ph.D,associate professor.Her main research interests include signal processing and educational data mining.
  • Supported by:
    National Natural Science Foundation of China(62277032).

PDF (PC)

197

摘要： 知识追踪要求基于学习者的历史作答情况来预测未来的答题表现,并评估知识状态的变化。探索学习者知识状态的变化有助于实现个性化服务,如课程推荐和试题推荐。然而,现有的大多数知识追踪模型在建模时考虑的特征不够全面,不能综合衡量学习者知识状态的变化。针对这一问题,提出一种新的知识追踪模型——基于试题-知识点异构图和多特征融合的知识追踪模型(EKMFKT)。具体而言,从学习者的学习过程出发,研究了两种行为特征(尝试次数和提示次数)以及两种时间特征(响应时间和间隔时间)对知识状态的影响。然后,设计了学习门和遗忘门,以模拟知识的获取和遗忘,全面更新知识状态的变化。另外,对于模型的输入,设计了基于试题-知识点异构图的图嵌入方法来预训练试题表示,使得模型的输入保持试题和知识点的关联。在两个公开数据集上的实验结果表明,EKMFKT在预测性能上优于现有模型。通过引入多个特征并确保试题与知识点的关联,EKMFKT使知识状态的变化更合理,增强了模型的可解释性。

关键词: 知识追踪, 异构图, 学习行为, 时间特征, 遗忘行为

Abstract: Knowledge tracing(KT) aims to predict a learner’s future performance based on their historical responses and assess changes in their knowledge state.Exploring these changes facilitates personalized services,such as course and exercise recommendations.However,most existing knowledge tracing models do not consider comprehensive features,leading to incomplete assessments of a learner’s knowledge state changes.To address this issue,a new knowledge tracing model－knowledge tracing model based on exercise-knowledge point heterogeneous graph and multi-feature fusion(EKMFKT)is propose.Specifically,we study two behavioral features(attempt and hint) and two temporal features(response time and interval time) and their impact on the knowledge state.To simulate knowledge acquisition and forgetting,we design learning and forgetting gates,which comprehensively update the knowledge state.For model inputs,a graph embedding method based on the question-knowledge point heteroge-neous graph is designed to pre-train question representations,preserving the associations between questions and knowledge points.Experimental results on two public datasets demonstrate that EKMFKT outperforms existing models in predictive performance.By incorporating multiple features and ensuring the connection between question and knowledge point,EKMFKT provides a more reasonable representation of knowledge state changes,enhancing the interpretability of the model.

Key words: Knowledge tracing, Heterogeneous graph, Learning behavior, Time feature, Forgetting behavior

中图分类号: 

  • G40-057
[1]WANG Y,ZHU M X,YANG S H,et al.Review and Perfor-mance Comparison of Deep Knowledge Tracing Models[J].Ruan Jian Xue Bao/Journal of Software,2023,34(3):1365-1395.
[2]ABDELRAHMAN G,WANG Q,NUNES B.Knowledge trac-ing:A survey[J].ACM Computing Surveys 2023,55(11):1-37.
[3]WU Z,LI M,TANG Y,et al.Exercise recommendation based on knowledge concept prediction [J].Knowledge-Based Systems,2020,210:106481.
[4]REN Y,LIANG K,SHANG Y,et al.MulOER-SAN:2-layermulti-objective framework for exercise recommendation with self-attention networks [J].Knowledge-Based Systems,2023,260:110117.
[5]SONG X,LI J,CAI T,et al.A survey on deep learning-based knowledge tracing [J].Knowledge-Based Systems,2022,258:110036.
[6]ZHANG Y,YANG Q.A survey on multi-task learning [J].IEEE Transactions on Knowledge and Data Engineering,2021,34(12):5586-5609.
[7]DEVLIN J,CHANG M W,LEE K,et al.BERT:Pre-training of deep bidirectional transformers for language understanding [C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1(Long and Short Papers).Minneapolis,MN:Association for Computational Linguistics,2019:4171-4186.
[8]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas,NV:IEEE,2016:770-778.
[9]SHEN S,LIU Q,CHEN E,et al.Learning process-consistentknowledge tracing [C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.2021:1452-1460.
[10]XU B,HUANG Z,LIU J,et al.Learning behavior-orientedknowledge tracing[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2023:2789-2800.
[11]CORBETT A T,ANDERSON J R.Knowledge tracing:Mode-ling the acquisition of procedural knowledge [J].User Modeling and User-adapted Interaction,1994,4:253-278.
[12]PAVLIK JR P I,CEN H,KOEDINGER K R.Performance Factors Analysis--A New Alternative to Knowledge Tracing[C]//Conference on Artificial Intelligence in Education:Building Learning Systems That Care:from Knowledge Representation to Affective Modelling.2009:531-538.
[13]EMBRETSON S E,REISE S P.Item response theory[M].Psychology Press,2013.
[14]PIECH C,BASSEN J,HUANG J,et al.Deep knowledge tracing [J].Advances in Neural Information Processing Systems,2015,25:505-513.
[15]LIU Y,YANG Y,CHEN X,et al.Improving knowledge tracing via pre-training question embeddings [C]//Proceedings of the 30th International Joint Conference on Artificial Intelligence(IJCAI).2021:1577-1583.
[16]LIU Q,HUANG Z,YIN Y,et al.Ekt:Exercise-aware know-ledge tracing for student performance prediction [J].IEEE Transactions on Knowledge and Data Engineering,2019,33(1):100-115.
[17]YAN Q Y,SI Y Q,YUAN G.Student-Problem AssociationBased Heterogeneous Graph Knowledge Tracing Model[J].Acta Electronica Sinica,2023,51(12):3549-3556.
[18]GHOSH A,HEFFERNAN N,LAN A S.Context-aware attentive knowledge tracing [C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2020:2330-2339.
[19]NAGATANI K,ZHANG Q,SATO M,et al.Augmentingknowledge tracing by considering forgetting behavior [C]//The World Wide Web Conference.2019:3101-3107.
[20]ZHAO W,XIA J,JIANG X,et al.A novel framework for deep knowledge tracing via gating-controlled forgetting and learning mechanisms [J].Information Processing & Management,2023,60(1):103-114.
[21]WANG X,JI H,SHI C,et al.A survey on heterogeneous network representation learning [J].IEEE Transactions on Know-ledge and Data Engineering,2020,32(12):2306-2324.
[22]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality [J].Advances in Neural Information Processing Systems,2013,26:3111-3119.
[23]PEROZZI B,AL-RFOU R,SKIENA S.Deepwalk:Online lear-ning of social representations [C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2014:701-710.
[24]TANG J,QU M,WANG M,et al.Line:Large-scale information network embedding [C]//Proceedings of the 24th International Conference on World Wide Web.2015:1067-1077.
[25]GROVER A,LESKOVEC J.node2vec:Scalable feature learning for networks [C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mi-ning.2016:855-864.
[26]DONG Y,CHAWLA N V,SWAMI A.metapath2vec:Scalable representation learning for heterogeneous networks [C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2017:135-144.
[27]FALMAGNE J C,COSYN E,DOIGNON J P,et al.The assessment of knowledge,in theory and in practice [C]//IEMC’03 Proceedings:Managing Technologically Driven Organizations:The Human Side of Innovation and Change(IEEE Cat.No.03CH37502).IEEE,2003:609-615.
[28]BAKER R S,ROLL I,CORBETT A T,et al.Do performancegoals lead students to game the system? [C]//International Conference on Artificial Intelligence in Education.2005:57-64.
[29]ZADEH A,CHEN M,PORIA S,et al.Tensor fusion network for multimodal sentiment analysis [C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Proces-sing.2017:1103-1114.
[30]HOCHREITER S,SCHMIDHUBER J.Long short-term memory [J].Neural Computation,1997,9(8):1735-1780.
[31]CHO K,VAN MERRIENBOER B,GULCEHRE C,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation [C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Proces-sing(EMNLP).2014:1724-1734.
[32]LOFTUS G R.Evaluating forgetting curves [J].Journal of Experimental Psychology:Learning,Memory,and Cognition,1985,11(2):397-406.
[33]WANG M,ZHENG D,YE Z,et al.Deep Graph Library:AGraph-Centric,Highly-Performant Package for Graph Neural Networks [J].arXiv:1909.01315,2019.
[34]GLOROT X,BENGIO Y.Understanding the difficulty of trai-ning deep feedforward neural networks [C]//Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics.JMLR Workshop and Conference Proceedings,2010:249-256.
[35]YEUNG C K,YEUNG D Y.Addressing two problems in deep knowledge tracing via prediction-consistent regularization [C]//Proceedings of the Fifth Annual ACM Conference on Learning at Scale.2018:1-10.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发