Abstract
This paper presents a study that uses unsupervised machine learning techniques to analyse CoI presence indicators (Social Presence, Teacher Presence and Cognitive Presence) in a Moodle forum. The objective of this study is to identify the profiles of the participants using unsupervised learning algorithms that detect patterns and common characteristics among them. To accomplish this, a plugin was developed in the Moodle forum to enable the meta-annotation of CoI presence indicators. Following that, various unsupervised learning algorithms, including Hierarchical clustering, Canopy, Cobweb, simple K-means, and more, were evaluated to identify the most suitable algorithm for detecting similar characteristics among groups of users in terms of their participation and activity levels in the forum and the topics they are most interested in and participate. Utilizing K-means, it became possible to determine whether the identified groups reflected varying levels of participation and particular user characteristics. Acquiring an understanding of user engagement and behavioral patterns provides valuable insights into community dynamics and leads to the development of strategies that enhance the online learning experience.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akyol, Z., et al.: A response to the review of the community of inquiry framework. J. Distance Educ. 23(2), 123–135 (2009)
Anggraeni, D.M., Sole, F.B.: E-Learning Moodle, Media Pembelajaran Fisika Abad 21. J. Penelit. dan Pengkaj. Ilmu Pendidik. e-Saintika 1, 2 (2018). https://doi.org/10.36312/e-saintika.v1i2.101
Bandura, A.: Social cognitive theory: an agentic perspective. Annu. Rev. Psychol. 52(1), 1–26 (2001). https://doi.org/10.1146/annurev.psych.52.1.1
Chang-Tik, C.: An analysis of discipline and personality in blended environments: do they interact differently in the teaching, cognitive, and social presences? Can. J. Learn. Technol. 46(1), 1–19 (2020). https://doi.org/10.21432/cjlt27883
Chen, Y., et al.: Discovering MOOC learner motivation and its moderating role. Behav. Inf. Technol. 39(12), 1257–1275 (2020). https://doi.org/10.1080/0144929X.2019.1661520
Dhika, H., et al.: Ease evaluation using the best moodle learning management system with data mining concepts. 944–952 (2020). https://doi.org/10.2991/ASSEHR.K.200129.117
Fauszt, T., et al.: Increasing the prediction power of Moodle machine learning models with self. Int. J. Emerg. Technol. Learn. 16(24), 23–39 (2021)
Geng, S., et al.: Investigating self-directed learning and technology readiness in blending learning environment. Int. J. Educ. Technol. High. Educ. 16, 1 (2019). https://doi.org/10.1186/s41239-019-0147-0
Kim, G., Gurvitch, R.: Online education research adopting the community of inquiry framework: a systematic review. 72(4), 395–409 (2020). https://doi.org/10.1080/00336297.2020.1761843
Mohd Radzi, S.F., et al.: Comparison of classification algorithms for predicting autistic spectrum disorder using WEKA modeler. BMC Med. Inform. Decis. Mak. 22(1), 1–15 (2022). https://doi.org/10.1186/s12911-022-02050-x
Nalli, G., et al.: Application of machine learning to the learning analytics of the Moodle platform to create heterogeneous groups in on-line courses. Ital. J. Educ. Res. 156–173 (2019). https://doi.org/10.7346/SIRD-2S2019-P158
Purwoningsih, T., et al.: Online learners’ behaviors detection using exploratory data analysis and machine learning approach. In: Proceeding of 2019 4th International Conference on Informatics Computer ICIC 2019 (2019). https://doi.org/10.1109/ICIC47613.2019.8985918
Rivas, A., et al.: Students performance analysis based on machine learning techniques. Commun. Comput. Inf. Sci. 1011, 428–438 (2019). https://doi.org/10.1007/978-3-030-20798-4_37/COVER
Santos, O.C., Boticario, J.G.: Supporting a collaborative task in a web-based learning environment with Artificial Intelligence and User Modelling techniques. Informática Educ. nuevos retos, 2004, ISBN 84–7723–653–4. 71 (2004)
Sha, L., et al.: Assessing Algorithmic Fairness in Automatic Classifiers of Educational Forum Posts. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics). 12748 LNAI, 381–394 (2021). https://doi.org/10.1007/978-3-030-78292-4_31/COVER
Vásquez-Bermúdez, M., et al.: Effectiveness of monitoring indicators in the architecture of a collaborative system. Commun. Comput. Inf. Sci. 1658(CCIS), 191–202 (2022). https://doi.org/10.1007/978-3-031-19961-5_14/COVER
Wertz, R.E.H.: Learning presence within the Community of Inquiry framework: an alternative measurement survey for a four-factor model. Internet High. Educ. 52, 100832 (2022). https://doi.org/10.1016/J.IHEDUC.2021.100832
Yanacón-Atía, D., et al.: Indicadores colaborativos individuales y grupales para Moodle Individual and group collaborative indicators for Moodle (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vásquez-Bermúdez, M., Aguirre-Munizaga, M., Hidalgo-Larrea, J. (2023). Analysis of CoI Presence Indicators in a Moodle Forum Using Unsupervised Learning Techniques. In: Valencia-García, R., Bucaram-Leverone, M., Del Cioppo-Morstadt, J., Vera-Lucio, N., Centanaro-Quiroz, P.H. (eds) Technologies and Innovation. CITI 2023. Communications in Computer and Information Science, vol 1873. Springer, Cham. https://doi.org/10.1007/978-3-031-45682-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-45682-4_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45681-7
Online ISBN: 978-3-031-45682-4
eBook Packages: Computer ScienceComputer Science (R0)