Analysis of Student Engagement in Virtual Learning Environments for Community Detection

• Bernadete Aquino Universidade Federal de Juiz de Fora https://orcid.org/0000-0002-6206-7003
• Victor Stroele Federal University of Juiz de Fora https://orcid.org/0000-0001-6296-8605
• Jairo Souza Universidade Federal de Juiz de Fora https://orcid.org/0000-0002-0911-7980

DOI: https://doi.org/10.5753/cbie.sbie.2020.952

Abstract

There is an increasing number of courses taught using virtual lear-ning environments. However, these environments face the challenge of keepingstudents motivated and engaged. A huge amount of data is generated by theseenvironments that can be used to discover patterns regarding student engage-ment. In this work, a model based on undirected graphs was proposed, where theelements represent students and their connections are similarity in their beha-vior. The Label Propagation algorithm was used to group students based onthree engagement metrics. A quantitative analysis was carried out to identifystudents who are not engaged who may need help. The results point to a signi-ficant difference concerning students’ actions that represent the phenomenon ofengagement between students with better and worse performance.

Keywords: Educational Data Mining, Engagement, Label Propagation Algorithm

References

[Brown et al. 2015] Brown, R., Lynch, C., Wang, Y., Eagle, M., Albert, J., Barnes, T., Baker,R., Bergner, Y., and McNamara, D. (2015). Communities of performance & communities of preference. InCEUR Workshop Proceedings, volume 1446. CEUR-WS. 8thInternational Conference on Educational Data Mining, EDM 2015 ; Conference date:26-06-2015 Through 29-06-2015.


[Chai et al. 2019] Chai, Y., Lei, C., and Yin, C. (2019). Study on the influencing factors of online learning effect based on decision tree and recursive feature elimination. pages 52–57.


[Costa et al. 2019] Costa, J., Bernardini, F., Artigas, D., and Viterbo, J. (2019). Miningdirect acyclic graphs to find frequent substructures — an experimental analysis on educational data. Information Sciences, 482.


[Gardner and Brooks 2018] Gardner, J. and Brooks, C. (2018). Coenrollment networks andtheir relationship to grades in undergraduate education. In Proceedings of the 8th International Conference on Learning Analytics and Knowledge, LAK ’18, page 295–304,New York, NY, USA. Association for Computing Machinery.


[Gitinabard et al. 2017] Gitinabard, N., Xue, L., Lynch, C., Heckman, S., and Barnes, T.(2017). A social network analysis on blended courses.


[Hernández-Blanco et al. 2019] Hernández-Blanco, A., Herrera-Flores, B., Tomás, D., andNavarro-Colorado, B. (2019). A systematic review of deep learning approaches to educational data mining.Complexity, pages 1–22.


[Jiang et al. 2014] Jiang, S., Fitzhugh, S. M., and Warschauer, M. (2014). What is the source of social capital? Workshop on Graph-Based Educational Data Mining, 14.


[Jokar and Mosleh 2018] Jokar, E. and Mosleh, M. (2018). Community detection in social networks based on improved label propagation algorithm and balanced link density.Physics Letters A.


[Jokar and Mosleh 2019] Jokar, E. and Mosleh, M. (2019). Community detection in socialnetworks based on improved label propagation algorithm and balanced link density.Physics Letters A, 383.


[Kovanovic et al. 2014] Kovanovic, V., Joksimovic, S., Gasevic, D., and Hatala, M. (2014).What is the source of social capital?Workshop on Graph-Based Educational DataMining.


[Lynch et al. 2017] Lynch, C., Barnes, T., Xue, L., and Gitinabard, N. (2017). Graph-based educational data mining (g-edm 2017) proceedings.


[Moubayed et al. 2018] Moubayed, A., Injadat, M., Shami, A., and Lutfiyya, H. (2018).Relationship between student engagement and performance in e-learning environment using association rules. pages 1–6.


[Muir et al. 2019] Muir, T., Milthorpe, N., Stone, C., Dyment, J., Freeman, E., andHopwood, B. (2019). Chronicling engagement: students’ experience of online lear-ning over time. Distance Education, 40(2):262–277.


[Oliveira et al. 2019a] Oliveira, J., Alexandrino, R., and Ambrósio, A. (2019a). A survey of applications that use graph-based educational data mining.Brazilian Symposiumon Computers in Education (Simpósio Brasileiro de Informática na Educação - SBIE),30(1):1401.


[Oliveira et al. 2019b] Oliveira, P., Souza, A., and Rodrigues, R. (2019b). Identificação de pesquisas referentes ao engajamento de alunos em plataformas de lms e suas relações com o desempenho acadêmico.Brazilian Symposium on Computers in Education(Simpósio Brasileiro de Informática na Educação - SBIE), 30(1):1631.


[Patel et al. 2017] Patel, N., Sellman, C., and Lomas, D. (2017). Mining frequent learning pathways from a large educational dataset.


[Saraiya and Ganage 2018] Saraiya, P. R. and Ganage, Y. (2018). Study of clustering techniques in the data mining domain. International Journal of Computer Science andMobile Computing, 7.


[Vytasek et al. 2020] Vytasek, J. M., Patzak, A., and Winne, P. H. (2020). Analytics for Student Engagement, pages 23–48. Springer International Publishing, Cham.


[Zhu et al. 2020] Zhu, Y., Zhang, J. H., Au, W., and Yates, G. (2020). University students’online learning attitudes and continuous intention to undertake online courses: a self-regulated learning perspective.Educational Technology Research and Development,68:1485–1519.