基于学生知识追踪的多指标习题推荐算法

doi:10.11959/j.issn.1000-0801.2022234

电信科学 ›› 2022, Vol. 38 ›› Issue (9): 129-143.doi: 10.11959/j.issn.1000-0801.2022234

基于学生知识追踪的多指标习题推荐算法

诸葛斌, 尹正虎, 斯文学, 颜蕾, 董黎刚, 蒋献

浙江工商大学信息与电子工程学院，浙江杭州 310020

修回日期:2022-06-27 出版日期:2022-09-20 发布日期:2022-09-01
作者简介:诸葛斌（1976- ），男，博士，浙江工商大学信息与电子工程学院教授，主要研究方向为网络和通信技术、互联网技术和网络安全
尹正虎（1997- ），男，浙江工商大学信息与电子工程学院硕士生，主要研究方向为在线教育、自然语言处理和个性化推荐
斯文学（1996- ），女，浙江工商大学信息与电子工程学院硕士生，主要研究方向为在线教育、数据分析和个性化推荐
颜蕾（1996- ），女，浙江工商大学信息与电子工程学院硕士生，主要研究方向为教育数据挖掘、深度学习和机器学习
董黎刚（1972- ），男，博士，浙江工商大学信息与电子工程学院教授，IEEE 和IEEE-CS成员，中国电子学会高级会员，浙江计算机学会理事，主要研究方向为智能网络、在线教育
蒋献（1988- ），男，浙江工商大学信息与电子工程学院讲师、实验员，主要研究方向为在线教育
基金资助:
浙江省重点研发计划项目(2021C01036);浙江省自然科学基金资助项目(LY18F010006);浙江省新型网络标准与应用技术重点实验室项目(2013E10012);浙江工商大学高等教育研究课题(Xgy21012)

Student knowledge tracking based multi-indicator exercise recommendation algorithm

Bin ZHUGE, Zhenghu YIN, Wenxue SI, Lei YAN, Ligang DONG, Xian JIANG

College of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou 310020, China

Revised:2022-06-27 Online:2022-09-20 Published:2022-09-01
Supported by:
The Key Research and Development Program of Zhejiang Province(2021C01036);Natural Science Foundation of Zhejiang Province(LY18F010006);Zhejiang Key Laboratory of New Network Standards and Application Technology(2013E10012);Higher Education Research Project of Zhejiang Gongshang University(Xgy21012)

摘要/Abstract

摘要：

个性化习题推荐是教育信息化时代的重要课题，传统的习题推荐算法忽略了学生在学习过程中的遗忘规律，未能充分挖掘学生的知识掌握水平和相似学生的共性特征，推荐习题的评价指标单一，推荐习题的新颖度和多样性不足，不能合理地促进学生对新知识的学习或帮助学生查缺补漏。针对上述缺陷，提出一种基于学生知识追踪的多指标习题推荐方法，该方法分为习题初筛和再过滤两个模块，围绕习题推荐的新颖度、难度以及多样性 3 个指标展开研究，首先构造了一个结合学生遗忘规律的知识概率预测（student forgetting behavior based knowledge concept coverage prediction，SF-KCCP）模型，保证推荐习题的新颖性；接着基于动态键值的知识追踪（dynamic key-value memory networks for knowledge tracing，DKVMN）模型精准挖掘学生的知识概念掌握水平，以保证推荐合适难度的习题；最后将基于用户的协同过滤（user-based collaborative filtering，UserCF）算法融入再过滤模块，利用学生群体之间的相似性实现推荐结果的多样性。通过大量的实验证明，所提方法比一些现有的基线模型取得了更好的性能。

关键词: 深度学习, 习题推荐, 知识追踪, 协同过滤

Abstract:

Personalized exercise recommendation was an important topic in the era of education informatization, the forgetting laws of students in the learning process were ignored by the traditional problem recommendation algorithm, which failed to fully tap the students’ knowledge mastery level and the common characteristics of similar students, insufficient, could not reasonably promote students’ learning of new knowledge or help students find and fill omissions.In view of the above defects, a multi-index exercise recommendation method based on student knowledge tracking was proposed, which was divided into two modules: preliminary screening and re-filtering of exercises, focusing on the novelty, difficulty and diversity of exercise recommendation.Firstly, a knowledge probability prediction (SF-KCCP) model combined with students’ forgetting law was constructed to ensure the novelty of the recommended exercises.Then, students’ knowledge and concept mastery level was accurately excavated based on the dynamic key-value knowledge tracking (DKVMN) model to ensure that exercises of appropriate difficulty were recommended.Finally, the user-based collaborative filtering (UserCF) algorithm was integrated into the re-filtering module, and the similarity between student groups was used to achieve the diversity of recommendation results.The proposed method is demonstrated by extensive experiments to achieve better performance than some existing baseline models.

Key words: deep learning, exercise recommendation, knowledge tracking, collaborative filtering

中图分类号:

TP301

诸葛斌, 尹正虎, 斯文学, 颜蕾, 董黎刚, 蒋献. 基于学生知识追踪的多指标习题推荐算法[J]. 电信科学, 2022, 38(9): 129-143.

Bin ZHUGE, Zhenghu YIN, Wenxue SI, Lei YAN, Ligang DONG, Xian JIANG. Student knowledge tracking based multi-indicator exercise recommendation algorithm[J]. Telecommunications Science, 2022, 38(9): 129-143.

图/表 16

图1

图3

图2

图4

图5

图6

图7

表1

表2

不同批尺寸下AUC值对比结果"

模型	ASST2009		STATICS2011		DouDouYun
模型	批尺寸	AUC	批尺寸	AUC	批尺寸	AUC
	8	0.791	8	$0 . 859$	8	0.782
DKVMN	16	0.824	16	0.820	16	0.837
	32	$0 . 845$	32	0.789	32	$0 . 852$
	64	0.813	64	0.764	64	0.819

表2

表3

模型预测性能对比"

模型	AUC			ACC			RMSE
模型	ASST09	STATICS	DouDY	ASST09	STATICS	DouDY	ASST09	STATICS	DouDY
BKT	0.713	0.742	0.725	0.718	0.735	0.729	0.457	0.426	0.446
DKT	0.769	0.814	0.786	0.762	0.801	0.783	0.446	0.415	0.430
DKVMN	$0 . 845$	$0 . 859$	$0 . 852$	$0 . 819$	$0 . 837$	$0 . 831$	$0 . 427$	$0 . 398$	$0 . 421$

表3

表4

习题推荐的准确性"

准确性	ASST2009		STATICS2011		DouDouYun
准确性	Mean	Std.D	Mean	Std.D	Mean	Std.D
SB-CF	0.493	0.213	0.688	0.210	0.708	0.202
EB-CF	0.655	0.101	0.390	0.213	0.533	0.255
DKT-CF	0.796	0.121	0.748	0.135	0.772	$0 . 113$
SKT-MIER	$0 . 894$	$0 . 076$	$0 . 864$	$0 . 074$	$0 . 847$	0.122

表4

表5

习题推荐的多样性"

多样性	ASST2009		STATICS2011		DouDouYun
多样性	Mean	Std.D	Mean	Std.D	Mean	Std.D
SB-CF	0.678	0.162	0.649	0.138	0.661	0.202
EB-CF	0.745	0.147	0.776	0.102	0.428	0.174
DKT-CF	0.857	$0 . 084$	0.847	0.079	0.670	0.219
SKT-MIER	$0 . 889$	0.089	$0 . 899$	$0 . 063$	$0 . 847$	$0 . 121$

表5

表6

图8

图9

图10

参考文献 28

[1]	BOBADILLA J , ALONSO S , HERNANDO A . Deep learning architecture for collaborative filtering recommender systems[J]. Applied Sciences, 2020,10(7): 2441.
[2]	NGUYEN L V , HONG M S , JUNG J J ,et al. Cognitive similarity-based collaborative filtering recommendation system[J]. Applied Sciences, 2020,10(12): 4183.
[3]	LI J , YE Z . Course recommendations in online education based on collaborative filtering recommendation algorithm[J]. Complexity, 2020:6619249.
[4]	吴云峰, 冯筠, 孙霞 ,等. 基于多分类器的迁移Bagging习题推荐[J]. 计算机应用, 2013,33(7): 1950-1954.
	WU Y F , FENG Y , SUN X ,et al. Online transfer-Bagging question recommendation based on hybrid classifiers[J]. Journal of Computer Applications, 2013,33(7): 1950-1954.
[5]	SEGAL A , KATZIR Z , GAL K ,et al. Edurank:a collaborative filtering approach to personalization in e-learning[C]// Proceedings of Conference on Educational Data Mining.[S.l.:s.n.], 2014.
[6]	OZAKI K . DINA models for multiple-choice items with few parameters:considering incorrect answers[J]. Applied Psychological Measurement, 2015,39(6): 431-447.
[7]	WANG F , LIU Q , CHEN E H ,et al. Neural cognitive diagnosis for intelligent education systems[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020,34(4): 6153-6161.
[8]	LIU Q , WU R Z , CHEN E H ,et al. Fuzzy cognitive diagnosis for modelling examinee performance[J]. ACM Transactions on Intelligent Systems and Technology, 2018,9(4): 1-26.
[9]	CHENG S , LIU Q , CHEN E H ,et al. DIRT:deep learning enhanced item response theory for cognitive diagnosis[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management.[S.l.:s.n.], 2019: 2397-2400.
[10]	PIECH C , BASSEN J , HUANG J ,et al. Deep knowledge tracing[J]. Advances in Neural Information Processing Systems, 2015(28).
[11]	YEUNG C K , YEUNG D Y . Addressing two problems in deep knowledge tracing via prediction-consistent regularization[C]// Proceedings of the 5th Annual ACM Conference on Learning at Scale. New York:ACM Press, 2018: 1-10.
[12]	ZHANG L , XIONG X L , ZHAO S Y ,et al. Incorporating rich features into deep knowledge tracing[C]// Proceedings of the 4th (2017) ACM Conference on Learning @ Scale. New York:ACM Press, 2017: 169-172.
[13]	LEE Y , CHOI Y , CHO J ,et al. Creating a neural pedagogical agent by jointly learning to review and assess[J]. arXiv preprint arXiv:1906.10910, 2019.
[14]	ZHANG J , SHI X , KING I ,et al. Dynamic key-value memory networks for knowledge tracing[C]// Proceedings of the 26th International Conference on World Wide Web.[S.l.:s.n.], 2017: 765-774.
[15]	ZHOU G R , ZHU X Q , SONG C R ,et al. Deep interest network for click-through rate prediction[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery ＆ Data Mining. New York:ACM Press, 2018: 1059-1068.
[16]	申情, 郭文宾, 楼俊钢 ,等. 考虑多层次潜在特征的个性化推荐模型[J]. 电信科学, 2022,38(2): 71-83.
	SHEN Q , GUO W B , LOU J G ,et al. Personalized recommendation model with multi-level latent features[J]. Telecommunications Science, 2022,38(2): 71-83.
[17]	LIU G , HAO T . User-based question recommendation for question answering system[J]. International Journal of Information and Education Technology, 2012,2(3): 243.
[18]	WEI S , YE N , ZHANG S ,et al. Item-based collaborative filtering recommendation algorithm combining item category with interestingness measure[C]// Proceedings of 2012 International Conference on Computer Science and Service System. Piscataway:IEEE Press, 2012: 2038-2041.
[19]	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 X R , XU Y , ZHU Q X . Personalized exercises recommendation method based on deep knowledge tracing[J]. Journal of Chinese Computer Systems, 2020,41(5): 990-995.
[20]	LV P , WANG X , XU J ,et al. Utilizing knowledge graph and student testing behavior data for personalized exercise recommendation[C]// Proceedings of ACM Turing Celebration Conference-China. New York:ACM Press, 2018: 53-59.
[21]	PARDOS Z A , HEFFERNAN N T . KT-IDEM:Introducing item difficulty to the knowledge tracing model[C]// Proceedings of International Conference on User Modeling,Adaptation,and Personalization. Heidelberg:Springer, 2011: 243-254.
[22]	KAMINSKAS M , BRIDGE D . Diversity,serendipity,novelty,and coverage:a survey and empirical analysis of beyond-accuracy objectives in recommender systems[J]. ACM Transactions on Interactive Intelligent Systems, 2017,7(1): 2.
[23]	NEDUNGADI P , REMYA M S . Incorporating forgetting in the personalized,clustered,bayesian knowledge tracing (PC-BKT) model[C]// Proceedings of 2015 International Conference on Cognitive Computing and Information Processing(CCIP). Piscataway:IEEE Press, 2015: 1-5.
[24]	WANG Z , ZHU J L , LI X ,et al. Structured knowledge tracing models for student assessment on coursera[C]// Proceedings of the 3rd (2016) ACM Conference on Learning @ Scale. New York:ACM Press, 2016: 209-212.
[25]	NAGATANI K , ZHANG Q , SATO M ,et al. Augmenting knowledge tracing by considering forgetting behavior[C]// Proceedings of WWW '19:The World Wide Web Conference.[S.l.:s.n.], 2019: 3101-3107.
[26]	HUO Y J , WONG D F , NI L M ,et al. Knowledge modeling via contextualized representations for LSTM-based personalized exercise recommendation[J]. Information Sciences, 2020 (523): 266-278.
[27]	ZHAO J J , BHATT S , THILLE C ,et al. Cold start knowledge tracing with attentive neural turing machine[C]// Proceedings of the Seventh ACM Conference on Learning @ Scale. New York:ACM Press, 2020: 333-336.
[28]	周晶, 孙喜民, 于晓昆 ,等. 知识图谱与数据应用:智能推荐[J]. 电信科学, 2019,35(8): 165-172.
	ZHOU J , SUN X M , YU X K ,et al. Knowledge graph and data application:intelligent recommendation[J]. Telecommunications Science, 2019,35(8): 165-172.

数据集	学生数/个	习题数/道	知识概念数/个	答题记录数/个
ASSISTment2009	4 151	110	378	325 637
Statics 2011	333	1 223	1 362	189 297
DouDouYun	8 333	1 287	300	5 166 342

新颖性	ASST2009		STATICS2011		DouDouYun
新颖性	Mean	Std.D	Mean	Std.D	Mean	Std.D
SB-CF	0.386	0.211	0.720	0.158	0.733	0.115
EB-CF	0.599	0.157	0.561	0.148	0.720	0.120
DKT-CF	0.685	0.212	0.827	0.113	0.826	0.104
SKT-MIER	0.863	0.077	0.899	0.077	0.928	0.073

基于学生知识追踪的多指标习题推荐算法

Student knowledge tracking based multi-indicator exercise recommendation algorithm

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 28

相关文章 15

Metrics

推荐阅读 0

[1]	卢敏, 胡娟, 张先超, 丁伟健, 乐光学. 基于用户多特征融合的个性化推荐模型[J]. 电信科学, 2023, 39(5): 101-115.
[2]	周杰, Esono Mikue Bernardo Esono, 王学英, 周惠婷, 罗宏. 基于SLM-PTS算法融合的NC-OFDM峰均比优化[J]. 电信科学, 2022, 38(7): 63-74.
[3]	李攀攀, 谢正霞, 乐光学, 刘鑫. 基于深度学习的无线通信接收方法研究进展与趋势[J]. 电信科学, 2022, 38(2): 1-17.
[4]	申情, 郭文宾, 楼俊钢, 余强国. 考虑多层次潜在特征的个性化推荐模型[J]. 电信科学, 2022, 38(2): 71-83.
[5]	陈志宏, 王明晓. 计算机视觉在智慧安防中的应用[J]. 电信科学, 2021, 37(8): 142-147.
[6]	唐博恒, 柴鑫刚. 基于云边协同的计算机视觉推理机制[J]. 电信科学, 2021, 37(5): 72-81.
[7]	孙姝君, 彭盛亮, 姚育东, 杨喜. 基于深度学习的调制识别综述[J]. 电信科学, 2021, 37(5): 82-90.
[8]	彭双, 王晓东, 彭宗举, 陈芬. 基于深度学习的快速QTMT划分[J]. 电信科学, 2021, 37(4): 73-81.
[9]	胡道允, 齐进, 陆钱春, 李锋, 房红强. 基于深度学习的流量工程算法研究与应用[J]. 电信科学, 2021, 37(2): 107-114.
[10]	张捷, 杨丽花, 王增浩, 呼博, 聂倩. 一种新型的基于深度学习的时变信道预测方法[J]. 电信科学, 2021, 37(1): 39-47.
[11]	李远宁,宁柏锋,董召杰. 电网机巡图像分析框架与深度学习方法[J]. 电信科学, 2020, 36(8): 167-174.
[12]	张婷婷,章坚武,郭春生,陈华华,周迪,王延松,徐爱华. 基于深度学习的图像目标检测算法综述[J]. 电信科学, 2020, 36(7): 92-106.
[13]	郭锐,冉凡春. 基于卷积神经网络的极化码译码算法[J]. 电信科学, 2020, 36(6): 119-124.
[14]	汪少敏,王铮,任华. 利用深度学习融合模型提升文本内容安全的研究[J]. 电信科学, 2020, 36(5): 25-30.
[15]	盛剑涛,陈茂飞,刘东鑫,汪来富,史国水,金华敏. 基于组合分类器的恶意域名检测技术[J]. 电信科学, 2020, 36(5): 47-55.