Personalized course recommendations based on a learner’s knowledge and personality

doi:10.3969/j.issn.1000-5641.2022.06.010

Abstract

Abstract:

Adaptive learning is an educational method that uses computer algorithms to coordinate interaction with learners, and provides customized learning resources and learning activities to address the unique needs of each learner. With the impact of COVID-19, adaptive learning has become increasingly important. One of the challenges with adaptive learning is how to provide personalized learning resources for learners—i.e., how to generate personalized recommendation for learners from a large set of learning resources. Existing methodologies mainly generate recommendations based on a learner’s knowledge level; however, this approach has some limitations. Firstly, when assessing a learner’s knowledge level, learners’ forgetting phenomenon has to date not been well modeled. Secondly, recommendations are generated separately from knowledge tracing tasks, ignoring the interconnectedness between these aspects. In addition, learners’ preferences for the type of learning resources and learning strategies is normally ignored if the knowledge level alone is used. To solve the aforementioned problems, this paper proposes a knowledge and personality incorporated multi-task learning framework (KPM) to boost course recommendations (i.e., the above-mentioned learning resources); the proposed method regards an enhanced knowledge tracing task (EKTT) as an auxiliary task to assist the primary course recommendation task (CRT). Specifically, using EKTT, we design a personalized forgetting controller to enhance the deep knowledge tracing model for accurately assessing a learner’s knowledge level. With CRT, we combine the learner’s knowledge level and sequential behavior with their personality adapted to the specific context to obtain learner’s profile; this data is subsequently used to generate a course recommendation list. Experimental results on real-world educational datasets demonstrate the superiority of our proposed method in terms of hit ratio (HR), normalized discounted cumulative gain (NDCG), and precision, indicating that our method can generate more personalized recommendations.

Key words: course recommendation, knowledge tracing, multi-task learning, personality, adaptive learning

CLC Number:

TP181

Qimin BAN, Wen WU, Wenxin HU, Hui LIN, Wei ZHENG, Liang HE. Personalized course recommendations based on a learner’s knowledge and personality[J]. Journal of East China Normal University(Natural Science), 2022, 2022(6): 87-101.

Figures/Tables 7

Fig.1

Fig.2

Table 1

Fig.3

Table 2

Table 3

Fig.4

References 37

1	KAPLAN A. Higher Education at the Crossroads of Disruption: The University of the 21st Century [M]. [S. l]: Emerald Group Publishing, 2021.
2	CARBONELL J R. AI in CAI: An artificial-intelligence approach to computer-assisted instruction. IEEE Transactions on Man-Machine Systems, 1970, 11 (4): 190- 202.
3	HUO Y J, WONG D F, NI L M, et al. Knowledge modeling via contextualized representations for LSTM-based personalized exercise recommendation. Information Sciences, 2020, (523): 266- 278.
4	LIU Q, TONG S, LIU C, et al. Exploiting cognitive structure for adaptive learning [C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2019: 627-635. DOI: 10.1145/3292500.3330922.
5	WU Z, LI M, TANG Y, et al. Exercise recommendation based on knowledge concept prediction. Knowledge-Based Systems, 2020, 210, 106481.
6	EBBINGHAUS H. Memory: A contribution to experimental psychology. Annals of Neurosciences, 2013, 20 (4): 155- 156.
7	HOCHREITER S, SCHMIDHUBER J. Long short-term memory. Neural Computation, 1997, 9 (8): 1735- 1780.
8	ZHANG Y, YANG Q. A survey on multi-task learning [J]. IEEE Transactions on Knowledge and Data Engineering, 2021. DOI: 10.1109/TKDE.2021.3070203.
9	DIGMAN J M. Personality structure: Emergence of the five-factor model. Annual Review of Psychology, 1990, 41 (1): 417- 440.
10	FURNHAM A. Personality and learning style: A study of three instruments. Personality and Individual Differences, 1992, 13 (4): 429- 438.
11	MOLLER L, SOLES C. Myers Briggs type preferences in distance learning education [J]. International Journal of Educational Technology, 2001, 2(2).
12	CHAMORRO-PREMUZIC T, FURNHAM A, LEWIS M. Personality and approaches to learning predict preference for different teaching methods. Learning and Individual Differences, 2007, 17 (3): 241- 250.
13	WU W, CHEN L, YANG Q C, et al. Inferring students’ personality from their communication behavior in Web-based learning systems. International Journal of Artificial Intelligence in Education, 2019, 29 (2): 189- 216.
14	ABYAA A, IDRISSI M K, BENNANI S. Learner modelling: Systematic review of the literature from the last 5 years. Educational Technology Research and Development, 2019, 67 (5): 1105- 1143.
15	GONG J, WANG S, WANG J, et al. Attentional graph convolutional networks for knowledge concept recommendation in MOOCs in a heterogeneous view [C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020: 79-88. DOI: 10.1145/3397271.3401057.
16	PANDEY S, LAN A, KARYPIS G, et al. Learning student interest trajectory for MOOC thread recommendation [C]//Proceedings of the 20th International Conference on Data Mining Workshops. IEEE, 2020: 400-407. DOI: 10.1109/ICDMW51313.2020.00062.
17	刘恒宇, 张天成, 武培文, 等. 知识追踪综述. 华东师范大学学报(自然科学版), 2019, (5): 1- 15.
18	PIECH C, BASSEN J, HUANG J, et al. Deep knowledge tracing. Advances in Neural Information Processing Systems, 2015, 28, 505- 513.
19	NAGATANI K, ZHANG Q, SATO M, et al. Augmenting Knowledge Tracing by Considering Forgetting Behavior [C]//Proceedings of the 28th International Conference on World Wide Web. 2019: 3101-3107. DOI: 10.1145/3308558.3313565.
20	GHOSH A, HEFFERNAN N, LAN A S. Context-aware attentive knowledge tracing [C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2020: 2330-2339. DOI: 10.1145/3394486.3403282.
21	PANDEY S, SRIVASTAVA J. RKT: Relation-aware self-attention for knowledge tracing [C]//Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 2020: 1205-1214. DOI: 10.1145/3340531.3411994.
22	HADASH G, SHALOM O S, OSADCHY R. Rank and rate: Multi-task learning for recommender systems [C]//Proceedings of the 12th ACM Conference on Recommender Systems. 2018: 451-454. DOI: 10.1145/3240323.3240406.
23	CHEN Z, WANG X, XIE X, et al. Co-attentive multi-task learning for explainable recommendation [C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2019: 2137-2143. DOI: 10.24963/ijcai.2019/296.
24	MENG W, YANG D, XIAO Y. Incorporating user micro-behaviors and item knowledge into multi-task learning for session-based recommendation [C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020 : 1091-1100. DOI: 10.1145/3397271.3401098.
25	WANG H, ZHANG F, ZHAO M, et al. Multi-task feature learning for knowledge graph enhanced recommendation [C]//Proceedings of the 28th International Conference on World Wide Web. 2019: 2000-2010. DOI: 10.1145/3308558.3313411.
26	GOSLING S D, RENTFROW P J, SWANN J W B. A very brief measure of the big-five personality domains. Journal of Research in Personality, 2003, 37 (6): 504- 528.
27	WU W, CHEN L. Implicit acquisition of user personality for augmenting movie recommendations [C]//Proceedings of the 23rd International Conference on User Modeling, Adaptation, and Personalization. Cham: Springer, 2015: 302-314. DOI: 10.1007/978-3-319-20267-9_25.
28	SHEN T, JIA J, LI Y, et al. Peia: Personality and emotion integrated attentive model for music recommendation on social media platforms [C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence. 2020, 34(01): 206-213. DOI: 10.1609/aaai.v34i01.5352.
29	YU Z, LIAN J, MAHMOODY A, et al. Adaptive user modeling with long and short-term preferences for personalized recommendation [C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2019: 4213-4219. DOI: 10.24963/ijcai.2019/585.
30	ZHOU G, MOU N, FAN Y, et al. Deep interest evolution network for click-through rate prediction [C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence. 2019, 33(01): 5941-5948. DOI: 10.1609/aaai.v33i01.33015941.
31	BEUTEL A, COVINGTON P, JAIN S, et al. Latent cross: Making use of context in recurrent recommender systems [C]//Proceedings of the 11th ACM International Conference on Web Search and Data Mining. 2018: 46-54. DOI: 10.1145/3159652.3159727.
32	RENDLE S. Factorization machines with libFM [J]. ACM Transactions on Intelligent Systems and Technology , 2012, 3(3): Article number 57. DOI 10.1145/2168752.2168771.
33	HE X, LIAO L, ZHANG H, et al. Neural collaborative filtering [C]//Proceedings of the 26th International Conference on World Wide Web. 2017: 173-182. DOI: 10.1145/3038912.3052569.
34	WILLMOTT C J, MATSUURA K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 2005, 30 (1): 79- 82.
35	JÄRVELIN K, KEKÄLÄINEN J. IR evaluation methods for retrieving highly relevant documents [C]//Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2000: 41-48. DOI: 10.1145/345508.345545.
36	WU W, CHEN L, ZHAO Y. Personalizing recommendation diversity based on user personality. User Modeling and User-Adapted Interaction, 2018, 28 (3): 237- 276.
37	MEHTA Y, MAJUMDER N, GELBUKH A, et al. Recent trends in deep learning based personality detection. Artificial Intelligence Review, 2020, 53 (4): 2313- 2339.

模型	数据集	A_Acc	S_AUC	E_MSE
DKT	POJ	0.646	0.538
DKT	LLS			0.0175
E_DKT	POJ	0.648	0.551
E_DKT	LLS			0.0173
Gain/%^⑥		0.3	2.4	1.1

模型	R_HR,5	R_HR,10	G_NDCG,5	G_NDCG,10	P₅	P₁₀
BPRMF	0.182	0.386	0.105	0.170	0.319	0.321
FM	0.178	0.369	0.110	0.171	0.317	0.321
LSTM	0.190	0.380	0.117	0.178	0.317	0.320
DIEN	0.204	0.401	0.120	0.183	0.321	0.322
KPM	0.212	0.414	0.127	0.191	0.34	0.343
Gain/%^⑥	3.9	3.2	5.8	4.4	5.9	6.5

模型	R_HR,5	R_HR,10	G_NDCG,5	G_NDCG,10	P₅	P₁₀
KPM_K	0.190	0.385	0.113	0.175	0.305	0.309
KPM_T	0.193	0.398	0.109	0.175	0.309	0.307
KPM_P	0.162	0.365	0.094	0.159	0.319	0.316
KPM	0.212	0.414	0.127	0.191	0.34	0.343