GNN-LS: A Learning Style Prediction in Online Environments using Graph Neural Networks

Bello Ahmad Muhammad

¹ Bayero University, Kano, Kano 700241, Nigeria

² School of Computer Science, Shaanxi Normal University, Xi’an, Shaanxi, 710062, China

Prediction of learners’ learning styles in online environments has several advantages, including steering learners on the proper path, motivating and engaging them while learning, and improving their learning results. It also helps instructors in the formation of personalized resource recommendations. As a result, predicting learners learning styles is necessary to aid in the personalization process. Existing approaches use either conventional or automatic approaches for learning style identifications. However, the large volume of data stored in online platforms has become a challenge in analyzing the behavior of learners and predicting their learning styles in the real world. Also, most of the existing approaches rely on a particular learning platform and can not be used in other platforms without technical assistance. In this paper, we propose GNN-LS, a new approach to identify and predict learners learning styles using a graph neural network. First, the graph embedding technique is used to capture the representation of learners and resources as a bipartite graph and encode them into low-dimensional representation. The encoded L-R sequences were given as input to the K-means clustering algorithm to identify and obtain labels as per FSLSM dimensions. Then, Graph neural network is trained to predict the learner’s learning style in the real world. The GNN-LS technique can be applied in a variety of educational systems and adapted to fit a variety of learning style models. Extensive experiments are run using the 2015 KDD Cup public available dataset to demonstrate the capabilities of GNN-LS. 5.31-15.68% improvements are achieved across all four FSLSM dimensions in accuracy.

Learning style, graph neural network, FSLSM, learners behavior

Bello Ahmad Muhammad, Bo Liu, Hafsa Kabir Ahmad, Mubarak Umar, and Kenan Qin (2022). GNN-LS: A Learning Style Prediction in Online Environments using Graph Neural Networks. Journal of Networking and Network Applications, Volume 2, Issue 4, pp. 172–182. https://doi.org/10.33969/J-NaNA.2022.020405.

[1] H. K. Ahmad, C. Qi, Z. Wu, and B. A. Muhammad, ”ABiNE-CRS: Course Recommender System in Online Education using At-tributed Bipartite Network Embedding,” Applied Intelligence, 2022, doi: 10.1007/s10489-022-03758-z.

[2] F. Rasheed and A. Wahid, “Learning style detection in E-learning systems using machine learning techniques,” Expert Syst. Appl., vol. 174, no. February, p. 114774, 2021, doi: 10.1016/j.eswa.2021.114774.

[3] V. Movchun, R. Lushkov, and N. Pronkin, “Prediction of individual learning style in e-learning systems: opportunities and limitations in dental education,” Educ. Inf. Technol., vol. 26, no. 3, pp. 2523–2537, 2021, doi: 10.1007/s10639-020-10372-4.

[4] E. ¨Ozpolat et al., “Integrating learning styles and adaptive e-learning system: Current developments, problems and opportunities,” Comput. Educ., vol. 9, no. 3, pp. 1–16, 2020, doi: 10.1016/j.tsc.2015.04.003.

[5] J. Feldman, A. Monteserin, and A. Amandi, “Automatic detection of learning styles: state of the art,” Artif. Intell. Rev., vol. 44, no. 2, pp. 157–186, 2015, doi: 10.1007/s10462-014-9422-6.

[6] M. Raleiras, A. H. Nabizadeh, and F. A. Costa, Automatic learning styles prediction: a survey of the State-of-the-Art (2006–2021), no. 0123456789. Springer Berlin Heidelberg, 2022.

[7] N. R. Ngatirin and Z. Zainol, “Automatic Detection of Learning Styles: A Decade Review on Data-driven Approaches,” J. Phys. Conf. Ser., vol. 1997, no. 1, 2021, doi: 10.1088/1742-6596/1997/1/012001.

[8] S. Wibirama, A. P. Sidhawara, G. Lukhayu Pritalia, and T. B. Adji, “A Survey of Learning Style Detection Method using Eye-Tracking and Machine Learning in Multimedia Learning,” 2020 Int. Symp. Community-Centric Syst. CcS 2020, pp. 0–5, 2020, doi: 10.1109/CcS49175.2020.9231447.

[9] B. Ahmad Muhammad, C. Qi, Z. Wu, and H. Kabir Ahmad, “GRL-LS: A learning style detection in online education using graph represen-tation learning,” Expert Syst. Appl., vol. 201, p. 117138, 2022, doi: https://doi.org/10.1016/j.eswa.2022.117138.

[10] B. A. Muhammad, Z. Wu, and H. K. Ahmad, “A Conceptual Framework for Detecting Learning Style in an Online Education Using Graph Repre-sentation Learning,” in Proceedings - 2020 International Conference on Networking and Network Applications, NaNA 2020, 2020, pp. 136–140, doi: 10.1109/NaNA51271.2020.00031.

[11] B. Hmedna, A. El Mezouary, and O. Baz, “A predictive model for the identification of learning styles in MOOC environments,” Cluster Comput., vol. 04, 2019, doi: 10.1007/s10586-019-02992-4.

[12] M. Raleiras et al., “A robust classification to predict learning styles in adaptive E-learning systems,” Educ. Inf. Technol., vol. 25, no. 2, pp. 437–448, 2020, doi: 10.1007/s10639-019-09956-6.

[13] Sabine Graf, “Adaptivity in Learning Management Systems Focussing on Learning Styles,” PhD Thesis, no. December 2007, 2007.

[14] J. Bernard, T. W. Chang, E. Popescu, and S. Graf, “Learning style Iden-tifier: Improving the precision of learning style identification through computational intelligence algorithms,” Expert Syst. Appl., vol. 75, pp. 94–108, 2017, doi: 10.1016/j.eswa.2017.01.021.

[15] I. A. Alshalabi, S. E. Hamada, K. Elleithy, I. Badara, and S. Moslehpour, “Automated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style,” Int. J. Interact. Mob. Technol., vol. 12(5), pp. 4–27, 2018, doi: https://doi.org/10.3991/ijim.v12i5.8186.

[16] H. Fasihuddin, G. Skinner, and R. Athauda, “Towards adaptive open learning environments: Evaluating the precision of identifying learning styles by tracking learners’ behaviours,” Educ. Inf. Technol., vol. 22, no. 3, pp. 807–825, 2017, doi: 10.1007/s10639-015-9458-5.

[17] S. Sweta and K. Lal, “Personalized Adaptive Learner Model in E-Learning System Using FCM and Fuzzy Inference System,” Int. J. Fuzzy Syst., vol. 19, no. 4, pp. 1249–1260, 2017, doi: 10.1007/s40815-017-0309-y.

[18] M. P. P. Liyanage, K. S. L. Gunawardena, and M. Hirakawa, “Using learning styles to enhance learning management systems,” Int. J. Adv. ICT Emerg. Reg., vol. 7, no. 2, p. 47, 2014, doi: 10.4038/icter.v7i2.7177.

[19] N. Ahmad, Z. Tasir, J. Kasim, and H. Sahat, “Automatic detection of learning style in learning management system by using literature-based method,” Procedia - Soc. Behav. Sci., vol. 103, pp. 181–189, 2013, doi: 10.1016/j.sbspro.2013.10.324.

[20] H. Shamsudin, U. K. Yusof, and M. Sabudin, “Improving Learning Style Prediction using Tree-based Algorithm with Hyperparameter Optimiza-tion,” vol. 12, no. 1, 2020.

[21] T. Sheeba and R. Krishnan, “Prediction of student learning style us-ing modified decision tree algorithm in E-learning system,” in ACM International Conference Proceeding Series, 2018, pp. 85–90, doi: 10.1145/3239283.3239319.

[22] I. J. H. Studies, K. Crockett, A. Latham, and N. Whitton, “On predicting learning styles in conversational intelligent tutoring systems using fuzzy decision trees,” J. Hum. Comput. Stud., vol. 97, pp. 98–115, 2017, doi: 10.1016/j.ijhcs.2016.08.005.

[23] O. Pantho, “Using Decision Tree C4 . 5 Algorithm to Predict VARK Learning Styles,” Int. J. Comput. Internet Manag., vol. 24, no. 2, pp. 58–63, 2016, [Online]. Available: http://cmruir.cmru.ac.th/bitstream/123456789/428/1/24n2Page58.pdf.

[24] H. Sharma and S. Kumar, “A Survey on Decision Tree Algorithms of Classification in Data Mining,” vol. 5, no. 4, pp. 2094–2097, 2016.

[25] A. A. Kalhoro, S. Rajper, and G. A. Mallah, “Detection of E- Learners ’ Learning Styles: An Automatic Approach using Decision Tree,” vol. 14, no. 8, pp. 420–425, 2016.

[26] P. Garc´ıa, A. Amandi, S. Schiaffino, and M. Campo, “Evaluat-ing Bayesian networks’ precision for detecting students’ learning styles,” Comput. Educ., vol. 49, no. 3, pp. 794–808, 2007, doi: 10.1016/j.compedu.2005.11.017.

[27] N. Kondo and T. Hatanaka, “Estimation of Students ’ Learning States using Bayesian Networks and Log Data of Learning Management System,” vol. 3, no. 2, pp. 35–49, 2019.

[28] A. E. Permanasari, I. Hidayah, and S. Nugraha, “A Student Modeling Based on Bayesian Network Framework for Characterizing Student Learning Style A Student Modeling based on Bayesian Network Frame-work for Characterizing Student Learning Style,” no. May 2015, 2014, doi: 10.1166/asl.2014.5702.

[29] L. X. Li and S. S. A. Rahman, “Students’ learning style detection using tree augmented naive Bayes,” R. Soc. Open Sci., vol. 5, no. 7, 2018, doi: 10.1098/rsos.172108.

[30] P. Garc´ıa, S. Schiaffino, and A. Amandi, “An enhanced Bayesian model to detect students ’ learning styles in Web-based courses,” pp. 305–315, 2008, doi: 10.1111/j.1365-2729.2007.00262.x.

[31] C. Carmona, G. Castillo, and E. Mill´an, “Designing a Dynamic Bayesian Network for modeling students’ Learning Styles,” Proc. - 8th IEEE Int. Conf. Adv. Learn. Technol. ICALT 2008, pp. 346–350, 2008, doi: 10.1109/ICALT.2008.116.

[32] J. Bernard, T. Chang, E. Popescu, and S. Graf, “Using Artificial Neural Networks to Identify Learning Styles *,” vol. 1, pp. 541–544, doi: 10.1007/978-3-319-19773-9.