Identificação de Perfis Comportamentais de Estudantes eIdentification of Behavioral Profiles of Students in a Brazilian MOOC Using the K-means Algorithm

Authors

DOI:

https://doi.org/10.18264/eadf.v16i1.2812

Keywords:

Educational data mining, Student engagement, Distance education, Course completion

Abstract

Massive Open Online Courses (MOOCs) expand access to specialized education, but still exhibit heterogeneous participation patterns and low completion rates. This study aims to identify interaction patterns among students in a Chemistry MOOC offered by a Brazilian platform and to interpret behavioral profiles associated with engagement and certification. Secondary data from 3,540 students were analyzed, obtained from profile, progress, grade, and access-log reports. After correlation analysis, material-access frequency was removed from clustering because of redundancy, while certificate issuance was retained as an external variable. K-means was applied to standardized attributes representing time in the course, proportion of completed activities, and questionnaire attempts. The choice of k = 2 considered the elbow method, internal validity indices, resampling stability, group balance, and interpretability. Two clusters were obtained, representing higher and lower engagement. Crossing these clusters with certificate issuance produced four interpretive profiles: Engaged, Strategic, Inactive, and Instrumental. The results distinguish algorithmically generated clusters from profiles interpreted afterward and provide evidence for pedagogical interventions tailored to observed participation patterns. 

 

Keywords: Distance education. Educational data mining. Student engagement. Course completion.

Downloads

Download data is not yet available.

Author Biography

Vanessa Faria de, Instituto Federal de Educação Ciência e Tecnologia do Rio Grande do Sul

Holds a PhD from the Postgraduate Program in Informatics in Education (PPGIE) at the Federal University of Rio Grande do Sul (UFRGS). Master's degree in Informatics from the Postgraduate Program in Informatics (PPGI) at the Federal Technological University of Paraná (UTFPR), in the area of ​​Applied Computing, with an emphasis on Software Engineering. Specialized in Inclusive Special Education, with an emphasis on Assistive Technologies, from the State University of Northern Paraná (UENP). Graduated in Information Systems from UENP – Bachelor's degree in Information Systems and Licentiate degree in Computer Science. Also completed a Licentiate degree in Mathematics in the Pedagogical Training Program at UTFPR. Currently, she is a full-time professor at the Federal Institute of Education, Science and Technology of Rio Grande do Sul (IFRS) at the Ibirubá Campus, and is on leave to pursue her PhD. She teaches courses in Computer Science, Integrated Technical Informatics at the High School level, Bachelor's Degree in Mathematics, and Specialization in Language and Technology Teaching. She is a member of the Alto Jacuí Interdisciplinary Computing Research Group. Her research interests include Educational Data Mining, Learning Analytics, Artificial Intelligence - Machine Learning and Deep Learning, Digital Systems, and Educational Robotics.

References

ALRAIMI, K. M.; ZO, H.; CIGANEK, A. P. Understanding the MOOCs continuance: the role of openness and reputation. Computers & Education, v. 80, p. 28–38, 2015. DOI: https://doi.org/10.1016/j.compedu.2014.08.006

CAGILTAY, N. E.; TOKER, S.; CAGILTAY, K. Exploring MOOC learners’ behavioural patterns considering age, gender and number of course enrolments: insights for improving educational opportunities. Open Praxis, v. 16, n. 1, p. 70–81, 2024. DOI: https://doi.org/10.55982/openpraxis.16.1.543

FELDER, R. M.; SILVERMAN, L. K. Learning and teaching styles in engineering education. Engineering Education, v. 78, n. 7, p. 674–681, 1988.

FERREIRA-SATLER, M. et al. Fuzzy ontologies-based user profiles applied to enhance e-learning activities. Soft Computing, v. 16, n. 7, p. 1129–1141, 2012. DOI: https://doi.org/10.1007/s00500-011-0788-y

HAMIM, T.; BENABBOU, F.; SAEL, N. Student profile modeling: an overview model. In: INTERNATIONAL CONFERENCE ON SMART CITY APPLICATIONS, 4., 2019. Proceedings [...]. New York: ACM, 2019. p. 1–9. DOI: https://doi.org/10.1145/3368756.3369075

HONEY, P.; MUMFORD, A. The manual of learning styles. Maidenhead: Peter Honey, 1982.

HUBERT, L.; ARABIE, P. Comparing partitions. Journal of Classification, v. 2, n. 1, p. 193–218, 1985. DOI: https://doi.org/10.1007/BF01908075

JAIN, A. K. Data clustering: 50 years beyond K-means. Pattern Recognition Letters, v. 31, n. 8, p. 651–666, 2010. DOI: https://doi.org/10.1016/j.patrec.2009.09.011

KIZILCEC, R. F.; PIECH, C.; SCHNEIDER, E. Deconstructing disengagement: analyzing learner subpopulations in massive open online courses. In: INTERNATIONAL CONFERENCE ON LEARNING ANALYTICS AND KNOWLEDGE, 3., 2013, Leuven. Proceedings [...]. New York: ACM, 2013. p. 170–179. DOI: https://doi.org/10.1145/2460296.2460330

KOLB, D. A. Experiential learning: experience as the source of learning and development. Englewood Cliffs: Prentice Hall, 1984.

LIU, J.; et al. Research on learner “emotion-behavior-ability” characteristics based on MOOC online education user profiles. Information Processing & Management, v. 62, n. 3, art. 104026, 2025. DOI: https://doi.org/10.1016/j.ipm.2024.104026

LUNA, J. M.; et al. Subgroup discovery in MOOCs: a big data application for describing different types of learners. Interactive Learning Environments, v. 30, n. 1, p. 127–145, 2022. DOI: https://doi.org/10.1080/10494820.2019.1643742

MARECA, P.; BORDEL, B. Students profiles and their behavior in MOOC platforms: MiriadaX platform. In: IBERIAN CONFERENCE ON INFORMATION SYSTEMS AND TECHNOLOGIES, 14., 2019, Coimbra. Proceedings [...]. Piscataway: IEEE, 2019. p. 1–6. DOI: https://doi.org/10.23919/CISTI.2019.8760696

RODRIGUES, R. L.; et al. Discovery engagement patterns MOOCs through cluster analysis. IEEE Latin America Transactions, v. 14, n. 9, p. 4129–4135, 2016. DOI: https://doi.org/10.1109/TLA.2016.7785943

ROUSSEEUW, P. J. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, v. 20, p. 53–65, 1987. DOI: https://doi.org/10.1016/0377-0427(87)90125-7

SHAH, D. By the numbers: MOOCs in 2018. Class Central, 2018. Disponível em: https://www.classcentral.com/report/mooc-stats-2018/. Acesso em: 03 jan 2026.

SILVA, J. M. C. da; et al. Learner engagement and demographic influences in Brazilian massive open online courses: Aprenda Mais platform case study. Analytics, v. 3, n. 2, p. 178–193, 2024. DOI: 10.3390/analytics3020010

TAN, Y.; et al. Learning profiles, behaviors and outcomes: investigating international students’ learning experience in an English MOOC. In: INTERNATIONAL SYMPOSIUM ON EDUCATIONAL TECHNOLOGY, 2018. Proceedings [...]. Piscataway: IEEE, 2018. p. 214–218. DOI: https://doi.org/10.1109/ISET.2018.00055

Downloads

Published

2026-09-10

How to Cite

Vanessa Faria de. (2026). Identificação de Perfis Comportamentais de Estudantes eIdentification of Behavioral Profiles of Students in a Brazilian MOOC Using the K-means Algorithm. EaD Em Foco, 16(1), e2812. https://doi.org/10.18264/eadf.v16i1.2812

Issue

Vol. 16 No. 1 (2026)

Section

Estudos de Caso

License

Copyright (c) 2026 EaD em Foco

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

All articles published in Revista EaD em Foco receive the license

Creative Commons - Atribuição 4.0 Internacional (CC BY 4.0).

All subsequent publications, complete or partial, must be made with the acknowledgment, in citations, of the Revista EaD em Foco as the original editor of the article.