[1]ZHANG Kai,LIU Yue,QIN Zhengchu,et al.Knowledge tracing model via exercise transfer representation[J].CAAI Transactions on Intelligent Systems,2024,19(4):974-982.[doi:10.11992/tis.202302002]
Copy

Knowledge tracing model via exercise transfer representation

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 19 Number of periods: 2024 4 Page number: 974-982 Column: 学术论文—知识工程 Public date: 2024-07-05
Title:
Knowledge tracing model via exercise transfer representation
Author(s):
ZHANG Kai;  LIU Yue;  QIN Zhengchu;  QIN Xinyi
School of Computer Science, Yangtze University, Jingzhou 434023, China
Keywords:
knowledge tracing; learning transfer mechanism; exercise representation; exercise transfer; sequence model; answer prediction; attention mechanism; threshold mechanism
CLC:
TP183
DOI:
10.11992/tis.202302002
Abstract:
In most knowledge tracing research, the representation of questions typically relies solely on explicit features such as the concepts contained within the questions, neglecting the implicit feature of the emphasis level on concepts and failing to characterize the degree of question transfer during the transfer process. This paper presents a knowledge tracing model via exercise transfer representation. In terms of the representation of the focus of the exercise, the additive attention mechanism is used to extract the focus of each concept in the exercise. In terms of exercise transfer, the multi-angle transfer degree of historical exercises is modeled by fusion of similarity and channel attention mechanism. In terms of transfer forgetting, a threshold mechanism is used to model the forgetting process of learning transfer. Finally, the exercise transfer representation is obtained to predict the learner’s future answering performance. Experimental results show that the proposed model outperforms six benchmark models across three real datasets, particularly excelling on the ASSISTments 2012 dataset with improvements ranging from 3.5% to 20.1% for area under the curve (AUC) and 2.3% to 18.5% for accuracy (ACC). The interpretability aspect is enhanced through graphical visualization of the question transfer representation generation pathway. The internal mechanisms of learning transfer modeled in this paper provide valuable insights for the design of knowledge tracing models.
References:
[1] LIU Qi, SHEN Shuanghong, HUANG Zhenya, et al. A survey of knowledge tracing[EB/OL]. (2021-05-06)[2023-01-05]. https://ar5iv.org/abs/2105.15106.pdf.
[2] 刘铁园, 陈威, 常亮, 等. 基于深度学习的知识追踪研究进展[J]. 计算机研究与发展, 2022, 59(1): 81–104
LIU Tieyuan, CHEN Wei, CHANG Liang, et al. Research progress in knowledge tracking based on deep learning[J]. Computer research and development, 2022, 59(1): 81–104
[3] RABINER L, JUANG B. An introduction to hidden Markov models[J]. IEEE ASSP magazine, 1986, 3(1): 4–16.
[4] CORBETT A T, ANDERSON J R. Knowledge tracing: modeling the acquisition of procedural knowledge[J]. User modeling and user-adapted interaction, 1994, 4(4): 253–278.
[5] 黄诗雯, 刘朝晖, 罗凌云, 等. 融合行为和遗忘因素的贝叶斯知识追踪模型研究[J]. 计算机应用研究, 2021, 38(7): 1993–1997
HUANG Shiwen, LIU Zhaohui, LUO Lingyun, et al. Research on Bayesian knowledge tracing model integrating behavior and forgetting factors[J]. Computer application research, 2021, 38(7): 1993–1997
[6] PIECH C, BASSEN J, HUANG J. Deep knowledge tracing[J]. Advances in neural information processing systems, 2015, 28: 19–23.
[7] ZHANG Jiani, SHI Xingjian, KING I, et al. Dynamic key-value memory networks for knowledge tracing[C]//Proceedings of the 26th International Conference on World Wide Web. New York: ACM, 2017: 765-774.
[8] 李浩君, 卢佳琪, 吴嘉铭. 融合学习过程特征的深度知识追踪方法[J]. 浙江工业大学学报, 2022, 50(3): 245–252
LI Haojun, LU Jiaqi, WU Jiaming, et al. In-depth knowledge tracing method integrating learning process characteristics[J]. Journal of Zhejiang University of Technology, 2022, 50(3): 245–252
[9] 宗晓萍, 陶泽泽. 基于掌握速度的知识追踪模型[J]. 计算机工程与应用, 2021, 57(6): 117–123
ZONG Xiaoping, TAO Zeze. Knowledge tracing model based on mastery speed[J]. Computer engineering and application, 2021, 57(6): 117–123
[10] 李浩君, 高鹏. 融合梯度提升回归树的深度知识追踪优化模型[J]. 系统科学与数学, 2021, 41(8): 2101–2112
LI Haojun, GAO Peng. Deep knowledge tracing optimization model integrated with gradient boosting regression tree[J]. Systems science and mathematics, 2021, 41(8): 2101–2112
[11] SUN Xia, ZHAO Xu, MA Yuna, et al. Muti-behavior features based knowledge tracking using decision tree improved DKVMN[C]//Proceedings of the ACM Turing Celebration Conference. Chengdu: ACM, 2019: 1-6.
[12] 姚梅林. 学习迁移研究的新进展[J]. 北京师范大学学报(社会科学版), 1994(5): 99–104
YAO Meilin. New progress in learning transfer research[J]. Journal of Beijing Normal University (social science edition), 1994(5): 99–104
[13] ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization[EB/OL]. (2014-09-08)[2023-01-06]. https://ar5iv.org/abs/1409.2329.pdf.
[14] 刘坤佳, 李欣奕, 唐九阳, 等. 可解释深度知识追踪模型[J]. 计算机研究与发展, 2021, 58(12): 2618–2629
LIU KunJia, LI Xinyi, TANG Jiuyang, et al. Interpretable deep knowledge tracing model[J]. Computer research and development, 2021, 58(12): 2618–2629
[15] YANG Yang, SHEN Jian, QU Yanru, et al. GIKT: a graph-based interaction model for knowledge tracing[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer, 2020: 299-315.
[16] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[J]. Advances in neural information processing systems, 2016, 29: 3844–3852.
[17] LIU Yunfei, YANG Yang, CHEN Xianyu, et al. Improving knowledge tracing via pre-training question embeddings[EB/OL]. (2020-12-09)[2023-01-05]. https://ar5iv.org/abs/2012.05031.pdf.
[18] 马骁睿, 徐圆, 朱群雄. 一种结合深度知识追踪的个性化习题推荐方法[J]. 小型微型计算机系统, 2020, 41(5): 990–995
MA Xiaorui, XU Yuan, ZHU Qunxiong. A personalized exercise recommendation method combined with deep knowledge tracing[J]. Small microcomputer system, 2020, 41(5): 990–995
[19] 邵小萌, 张猛. 融合注意力机制的时间卷积知识追踪模型[J]. 计算机应用, 2023, 43(2): 343–348
SHAO Xiaomeng, ZHANG Meng. Temporal convolutional knowledge tracing model with attention mechanism[J]. Journal of computer applications, 2023, 43(2): 343–348
[20] BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL]. (2018-03-04)[2023-01-06]. https://ar5iv.org/abs/1803.01271.pdf.
[21] 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. New York: ACM, 2020: 2330-2339.
[22] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30: 5998–6008.
[23] NAGATANI K, ZHANG Q, SATO M, et al. Augmenting knowledge tracing by considering forgetting behavior[C]//The World Wide Web Conference. New York: IW3C2, 2019: 3101-3107.
[24] 李晓光, 魏思齐, 张昕, 等. LFKT: 学习与遗忘融合的深度知识追踪模型[J]. 软件学报, 2021, 32(3): 818–830
LI Xiaoguang, WEI Siqi, ZHANG Xin, et al. LFKT: deep knowledge tracing model with learning and forgetting behavior merging[J]. Journal of software, 2021, 32(3): 818–830
[25] 王璨, 刘朝晖, 王蓓, 等. TCN-KT: 个人基础与遗忘融合的时间卷积知识追踪模型[J]. 计算机应用研究, 2022, 39(5): 1496–1500
WANG Can, LIU Zhaohui, WANG Bei, et al. TCN-KT: time convolutional knowledge tracing model for fusion of personal basis and forgetting[J]. Computer application research, 2022, 39(5): 1496–1500
[26] PANDEY S, SRIVASTAVA J. RKT: relation-aware self-attention for knowledge tracing[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. New York: ACM, 2020: 1205-1214.
[27] GAN W, SUN Y, PENG X, et al. Modeling learner’s dynamic knowledge construction procedure and cognitive item difficulty for knowledge tracing[J]. Applied intelligence, 2020, 50: 3894–3912.
[28] SCHMIDHUBER J, HOCHREITER S. Long short-term memory[J]. Neural comput, 1997, 9(8): 1735–1780.
[29] BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[EB/OL]. (2014-09-01)[2023-01-05]. https://ar5iv.org/abs/1409.0473.pdf.
[30] SU Yu, LIU Qingwen, LIU Qi, et al. Exercise-enhanced sequential modeling for student performance prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2018: 2435-2443.
[31] FENG M, HEFFERNAN N, KOEDINGER K. Addressing the assessment challenge with an online system that tutors as it assesses[J]. User modeling and user-adapted interaction, 2009, 19: 243–266.
[32] KOEDINGER K R, BAKER R S J, CUNNINGHAM K, et al. A data repository for the EDM community: the PSLC datashop[J]. Handbook of educational data mining, 2010, 43: 43–56.
[33] CHOI Y, LEE Y, SHIN D, et al. Ednet: a large-scale hierarchical dataset in education[C]//21st International Conference on Artificial Intelligence in Education. Cham: Springer, 2020: 69-73.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems