Enhancing personalized exercise recommendation with student and exercise portraits

Abstract

The exercise recommendation system is emerging as a promising application in online learning scenarios, providing personalized recommendations to assist students with explicit learning directions. Existing solutions generally follow a collaborative filtering paradigm, while the implicit connections between students (exercises) have been largely ignored. In this study, we aim to propose an exercise recommendation paradigm that can reveal the latent connections between student-student (exercise-exercise). Specifically, a new framework was proposed, namely personalized exercise recommendation with student and exercise portraits (PERP). It consists of three sequential and interdependent modules: Collaborative student exercise graph (CSEG) construction, joint random walk, and recommendation list optimization. Technically, CSEG is created as a unified heterogeneous graph with students’ response behaviors and student (exercise) relationships. Then, a joint random walk to take full advantage of the spectral properties of nearly uncoupled Markov chains is performed on CSEG, which allows for full exploration of both similar exercises that students have finished and connections between students (exercises) with similar portraits. Finally, we propose to optimize the recommendation list to obtain different exercise suggestions. After analyses of two public datasets, the results demonstrated that PERP can satisfy novelty, accuracy, and diversity.

Keywords

Educational data mining / Exercise recommend / Joint random walk / Nearly uncoupled Markov chains / Optimization / Personalized learning / Educational data mining / Exercise recommend / Joint random walk / Nearly uncoupled Markov chains / Optimization / Personalized learning

References

[1]	A.H. Nabizadeh, J.P. Leal, H.N. Rafsanjani, R.R. Shah. Learning path personalization and recommendation methods: A survey of the state-of-the-art. Expert Syst. Appl., 159 (2020), Article 113596. 1-20.
[2]	Q. Zhang, J. Lu, G.-Q. Zhang. Recommender systems in E-learning. Journal of Smart Environments and Green Computing, 1 (2) (Apr.2021), pp. 76-89.
[3]	H. Ma, Z.-X. Huang, W.-S. Tang, X.-X. Zhang. Exercise recommendation based on cognitive diagnosis and neutrosophic set. Proc. of 25th Intl. Conf. Computer Supported Cooperative Work in Design, Hangzhou, China(2022), pp. 1467-1472.
[4]	S.-Y. Huang, Q.-Q. Liu, J.-H. Chen, X.-G. Hu, Z.-T. Liu, W.-Q. Luo. A design of a simple yet effective exercise recommendation system in K-12 online learning. Proc. of 23rd Intl. Conf. Artificial Intelligence in Education, Durham, USA(2022), pp. 208-212.
[5]	Z.-Z. Li, H.-Y. Hu, Z.-P. Xia, et al. Exercise recommendation algorithm based on improved collaborative filtering. Proc. of the Intl. Conf. Advanced Learning Technologies, Tartu, Estonia(2021), pp. 47-49.
[6]	Z.-Z. Li, H.-Y. Hu, Z.-P. Xia, et al. Exercise recommendation method based on machine learning. Proc. of the Intl. Conf. Advanced Learning Technologies, Tartu, Estonia(2021), pp. 50-52.
[7]	T.-J. Gong, X.-X. Yao. Deep exercise recommendation model, Intl. Journal of Modeling and Optimization, 9 (1) (Feb.2019), pp. 18-23.
[8]	W.-T. Wang, H.-F. Ma, Y. Zhao, Z.-X. Li, X.-C. He. Tracking knowledge proficiency of students with calibrated Q-matrix. Expert Syst. Appl., 192 (Apr.2022), Article 116454. 1-11.
[9]	W.-T. Wang, H.-F. Ma, Y. Zhao, F.-Y. Yang, L. Chang. PERM: Pre-training question embeddings via relation map for improving knowledge tracing. Proc. of 27th Intl. Conf. Database Systems for Advanced Applications (2022), pp. 281-288. Online.
[10]	Z.-Y. Wu, M. Li, Y. Tang, Q.-Y. Liang. Exercise recommendation based on knowledge concept prediction. Knowl.-Based Syst., 210 (Dec.2020), Article 106481. 1-14.
[11]	Y.-J.Huo, D.F. Wong, L.M. Ni, L.S. Chao, J. Zhang. Knowledge modeling via contextualized representations for LSTM-based personalized exercise recommendation. Inf. Sci., 523(Jun. 2020), pp. 266-278.
[12]	Y.-H. Liu, H.-F. Ma, Y.-B. Jiang, Z.-X. Li. Learning to recommend via random walk with profile of loan and lender in P2P lending. Expert Syst. Appl., 174 (Jul.2021), Article 114763. 1-13.
[13]	A.N. Nikolakopoulos, G. Karypis, RecWalk: Nearly uncoupled random walks for Top-N recommendation, in: Proc. of 12th Intl. Conf. Web Search and Data Mining, Melbourne, Australia, 2019, pp. 150-158.
[14]	G.W. Stewart.On the sensitivity of nearly uncoupled Markov chains. W.J. Stewart (Ed.), Numerical Solution of Markov Chains, CRC Press, Boca Raton (1991), pp. 105-119.
[15]	H.-Y. Bi, H.-P. Ma, Z.-Y. Huang, et al. Quality meets diversity: A model-agnostic framework for computerized adaptive testing. in: Proc. of the IEEE Intl. Conf. Data Mining, Sorrento, Italy(2020), pp. 42-51.
[16]	Z.-Y. Huang, Q. Liu, C.-X. Zhai, et al. Exploring multi-objective exercise recommendations in online education systems. Proc. of 28th ACM Intl. Conf. Information and Knowledge Management, Beijing, China(2019), pp. 1261-1270.
[17]	Z.-Y.Wu, T. He, C.-J. Mao, C.-Q. Huang. Exam paper generation based on performance prediction of student group. Inf. Sci., 532(Sept. 2020), pp. 72-90.
[18]	Q. Liu, S.-W. Tong, C.-R. Liu, et al. Exploiting cognitive structure for adaptive learning. in: Proc. of 25th ACM SIGKDD Intl. Conf. Knowledge Discovery & Data Mining, Anchorage, USA(2019), pp. 627-635.
[19]	Y. Zhuang, Q. Liu, Z.-Y. Huang, Z. Li, S.-H. Shen, H.-P. Ma. Fully adaptive framework: Neural computerized adaptive testing for online education. in: Proc. of 36th AAAI Conf. Artificial Intelligence, Online(2022), pp. 4734-4742.
[20]	A. Ghosh, A.-S. Lan. BOBCAT: Bilevel optimization-based computerized adaptive testing. Proc. of 30th Intl. Joint Conf. Artificial Intelligence, Montreal, Canada(2021), pp. 2410-2417.
[21]	C.K. Yeung.Deep-IRT: Make deep learning based knowledge tracing explainable using item response theory. Proc. of 12th Intl. Conf. Educational Data Mining, Montreal, Canada(2019), pp. 683-686.
[22]	J. de la Torre. DINA model and parameter estimation: A didactic. J. Educ. Behav. Stat., 34 (1) (Mar.2009), pp. 115-130.
[23]	W.-B. Gao, Q. Liu, Z.-Y. Huang, et al. RCD: Relation map driven cognitive diagnosis for intelligent education systems. in: Proc. of 44th Intl. ACM SIGIR Conf. Research and Development in Information Retrieval, Online(2021), pp. 501-510.
[24]	F. Wang, Q. Liu, E.-H. Chen, et al. Neural cognitive diagnosis for intelligent education systems. Proc. of 34th AAAI Conf. Artificial Intelligence, New York, USA(2020), pp. 6153-6161.
[25]	S. Shishehchi, S.Y. Banihashem, N.A.M. Zin, S.A.M. Noah. Review of personalized recommendation techniques for learners in e-learning systems. Proc. of2011 Intl. Conf. Semantic Technology and Information Retrieval, Putrajaya, Malaysia(2021), pp. 277-281.
[26]	Y.-H. Wei, H.-F. Ma, Y.-K. Wang, Z.-X. Li, L. Chang. Multi-behavior recommendation with two-level graph attentional networks. in: Proc. of 27th Intl. Conf. Database Systems for Advanced Applications, Online(2022), pp. 248-255.
[27]	R.-Y. Zhang, H.-F. Ma, Q.-F. Li, Z.-X. Li, Y.-K. Wang. A knowledge graph recommendation model via high-order feature interaction and intent decomposition. Proc. of Intl. Joint Conf, Neural Networks (IJCNN), Padua, Italy(2022), pp. 1-7.
[28]	Y.-B. Jiang, H.-F. Ma, Y.-H. Liu, Z.-X. Li, L. Chang. Enhancing social recommendation via two-level graph attentional networks. Neurocomputing, 449(Aug. 2021), pp. 71-84.
[29]	Y.-B. Jiang, H.-F. Ma, X.-H. Zhang, Z.-X. Li, L. Chang. An effective two-way metapath encoder over heterogeneous information network for recommendation. Proc. of2022 Intl, Conf. Multimedia Retrieval, Newark, USA(2022), pp. 90-98.
[30]	K.I.B.Ghauth, N.A. Abdullah. Building an e-learning recommender system using vector space model and good learners average rating. Proc. of 9th IEEE Intl. Conf. Advanced Learning Technologies, Riga, Latvia(2009), pp. 194-196.
[31]	D.-W. Hu, S.-H. Gu, S.-T. Wang, W.-Y. Liu, E.-H. Chen. Question recommendation for user-interactive question answering systems. Proc. of 2nd Intl. Conf. Ubiquitous Information Management and Communication, Suwon, Korea(2008), pp. 39-44.
[32]	A. Esteban, A. Zafra, C. Romero. Helping university students to choose elective courses by using a hybrid multi-criteria recommendation system with genetic optimization. Knowl.-Based Syst., 194 (Apr.2020), Article 105385. 1-14.
[33]	J.C.W. Debuse, V.J. Rayward-Smith. Feature subset selection within a simulated annealing data mining algorithm. J. Intell. Inf. Syst., 9 (1) (Jul.1997), pp. 57-81.
[34]	A. Ghosh, N. Heffernan, A.S. Lan.Context-Aware attentive knowledge tracing. Proc. Oof 26th ACM SIGKDD Intl. Conf. Knowledge Discovery and Data Mining, Online(2020), pp. 2330-2339.
[35]	J. Stamper, A. Niculescu-Mizil, S. Ritter, G.J. Gordon, K.R. Koedinger. Challenge data set from KDD Cup2010 educational data mining challenge.
	[Online]
[36]	T. Cover, P. Hart. Nearest neighbor pattern classification. IEEE Trans. Inf. Theor., 13 (1) (Jan.1967), pp. 21-27.
[37]	M. Zhu, D.-S. Zhen, R. Tao, Y.-Q. Shi, X.-Y. Feng, Q. Wang. Top-N collaborative filtering recommendation algorithm based on knowledge graph embedding. Proc. of 14th Intl. Conf. Knowledge Management in Organizations, Zamora, Spain(2019), pp. 122-134.
[38]	Y.-H. Yang, C. Huang, L.-H. Xia, Y.-X. Liang, Y.-W. Yu, C.-L. Li. Multi-behavior hypergraph-enhanced transformer for sequential recommendation. Proc. of 28th ACM SIGKDD Conf. Knowledge Discovery and Data Mining, Washington, USA(2022), pp. 2263-2274.
[39]	C. Piech, J. Bassen, J. Huang, et al. Deep knowledge tracing. Proc. of 28th Intl. Conf. Neural Information Processing Systems (Montreal, Canada, 2015), pp. 505-513.
[40]	Y. Yin, L. Dai, Z.-Y. Huang, et al. Tracing knowledge instead of patterns: stable knowledge tracing with diagnostic transformer. Proc. of the ACM Web Conf. (Austin, USA, 2023), pp. 855-864.