INFERRING PRE-SERVICE TEACHERS’ LATENT DIGITAL COMPETENCE  FROM DIGITAL LEARNING TRACES: A STUDY COMBINING HIDDEN MARKOV  MODELS AND SELF - REGULATED LEARNING THEORY

Nguyen Hoai Nam; Nguyen Ha Nam

Nguyen Hoai Nam	nam.moet@gmail.com	VNU, University of Education Vietnam National University, Hanoi 144 Xuan Thuy, Cau Giay ward, Hanoi, Vietnam; Ministry of Education and Training 35 Dai Co Viet, Bach Mai ward, Hanoi, Vietnam
Nguyen Ha Nam*	namnh@vnu.edu.vn	Vietnam National University, Hanoi Hoa Lac, Hanoi, Vietnam

Summary:

This study proposes an approach that integrates hidden Markov model and self-regulated learning theory to infer the latent states of digital competence among pre-service teachers based on behavioral data collected from a learning management system. Data were gathered from two distinct 15-week courses: “Introduction to Informatics” (216 students, 498,050 events) and “Application of Information Technology in Teaching” (51 students, 16,878 events). The results demonstrate that Hidden Markov Models effectively identified distinct latent learning states, which were meaningfully interpreted as different levels of digital competence through the lens of the three phase self-regulated learning framework. This research contributes both methodologically, by introducing an integrated hidden Markov model - self-regulated learning analytical pipeline; and practically, by providing an objective, continuous, and behavior-based assessment tool for evaluating competence in higher education.

View file

Keywords:

Digital competence

hidden Markov model

Self-regulated learning

learning analytics

Learning management system

competence assessment.

Refers:

[1] ADL.(2023). xAPI Profiles. Advanced Distributed Learning Initiative. https://adlnet.github.io/xapi profiles/xapi-profiles-about.html.

[2] Baker, Ryan. S. & Yacef, Kalina. (2009). The state of educational data mining in 2009: A review and future visions. Journal of Educational Data Mining, 1(1), 3-17. https://doi.org/10.5281/zenodo.3554657.

[3] Blikstein, Paulo & Worsley, Marcelo. (2016). Multimodal learning analytics and education data mining: Using computational technologies to measure complex learning tasks. Journal of Learning Analytics, 3(2), 220–238. https://doi.org/10.18608/ jla.2016.32.11.

[4] Carretero, S., Vuorikari, R. & Punie, Y. (2017). DigComp 2.1: The Digital Competence Framework for Citizens with eight proficiency levels and examples of use. Publications Office of the European Union. https:// doi.org/10.2760/38842.

[5] IMS Global. (2022). IMS Caliper Analytics® Specification. IMS Global Learning Consortium. https://www. imsglobal.org/spec/caliper/v1p2.

[6] Lê Anh Vinh, Bùi Diệu Quỳnh, Đỗ Đức Lân, Đào Thái Lai & Tạ Ngọc Trí. (2021). Xây dựng khung năng lực số cho học sinh phổ thông Việt Nam. Tạp chí Khoa học Giáo dục Việt Nam, 17(1), 1–11.

[7] Le Thai, Hung, Dinh Thi Kim Thoa, Vu Phuong Lie & Nguyen Thi Phuong Vy. (2022). ICT competence of pre-service teachers in Vietnam: Structure and impact model. Journal of Educational and Social Research, 12(3), 172. https://doi.org/10.36941/jesr 2022-0076.

[8] Macfadyen, Leah. P. & Dawson, Shane. (2010). Mining LMS data to develop an “early warning system” for educators: A proof of concept. Computers & Education, 54(2), 588–599. https://doi.org/10.1016/j. compedu.2009.09.008.

[9] Matcha Wannisa, Gasevic Dragan, Nora Ayu Ahmad Uziz, Jelena Jovanovic & Pardo Abelardo. (2019). Analytics of learning strategies: Associations with academic performance and feedback. In Proceedings of the 9th International Conference on Learning Analytics & Knowledge (pp. 461-470). ACM. https://doi.org/10.1145/3303772.3303787.

[10] Ministry of Education and Training (MOET). (2025). Khung năng lực số cho người học. Hanoi.

[11] Moodle. (2023). Events API. Moodle Developer Resources. https://docs.moodle.org/dev/Events_ API

[12] Pintrich, Paul R. (2004). A conceptual framework for assessing motivation and self-regulated learning in college students. Educational Psychology Review, 16(4), 385–407. https://doi.org/10.1007/s10648-004 0006-x.

[13] Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257 286. https://doi.org/10.1109/5.18626.

[14] Siemens George, & Baker Ryan S. (2012). Learning analytics and educational data mining: Towards communication and collaboration. In Proceedings of the 2nd International Conference on Learning Analytics and Knowledge (pp. 252-254). ACM. https://doi.org/10.1145/2330601.2330661.

[15] Sillat Linda Helene, Tammets Kairit & Laanpere Mart. (2021). Digital competence assessment methods in higher education: A systematic literature review. Education Sciences, 11(8), 402. https://doi. org/10.3390/educsci11080402.

[16] Vuorikari, R., Kluzer, S. & Punie, Y. (2022). DigComp 2.2: The Digital Competence Framework for Citizens - With new examples of knowledge, skills and attitudes. Publications Office of the European Union. https://doi.org/10.2760/490274.

[17] Winne, P. H. (2014). Issues in researching self-regulated learning as patterns of events. Metacognition and Learning, 9(2), 229–237. https://doi.org/10.1007/ s11409-014-9113-3.

[18] Xing Wanli & Du Dongping. (2019). Dropout prediction in MOOCs: Using deep learning for personalized intervention. Journal of Educational Computing Research, 57(3), 547-570. https://doi. org/10.1177/0735633118757015.

[19] Zimmerman Barry J. (2002). Becoming a self-regulated learner: An overview. Theory Into Practice, 41(2), 64 70. https://doi.org/10.1207/s15430421tip4102_2.

Journal:

No. 12, December 2025

VIETNAM JOURNAL OF EDUCATIONAL SCIENCES

THE VIETNAM NATIONAL INSTITUTE OF EDUCATIONAL SCIENCES

INFERRING PRE-SERVICE TEACHERS’ LATENT DIGITAL COMPETENCE FROM DIGITAL LEARNING TRACES: A STUDY COMBINING HIDDEN MARKOV MODELS AND SELF - REGULATED LEARNING THEORY