FEATURES OF RESEARCHING BEHAVIORAL DIGITAL TRACES IN DISTANCE LEARNING SYSTEMS
DOI:
https://doi.org/10.28925/2663-4023.2025.31.1054Keywords:
digital footprints, distance learning, behavioral patterns, atypical behavior, predictive model, machine learning, academic risk, distance learning system (DLS), classification, educational analytics.Abstract
The article presents the results of research on the issue of analyzing behavioral digital traces (DST) in distance learning systems (DLS) of Ukrainian educational institutions. The conducted study proved the effectiveness of the proposed model of analyzing behavioral DST for identifying atypical learning behavior in DLS. The predictive model developed in the article is based on the assessment of the anomaly measure A(x) and the probabilistic interpretation of the results based on the use of logistic regression. The ability of the model to differentiate users by types of learning behavior in DLS is experimentally proven. The results of the simulation, performed on data from two Kyiv higher education institutions, confirmed the hypothesis of the feasibility of classifying students into three discrete categories. Namely, "stable", "irregular" and "risky" based on objective metrics of their digital activity in DLS. The visualization of the spatial distribution of observations in the coordinates of the features used in the simulation experiment presented in the article revealed clear clusters. These clusters corresponded to different behavioral patterns of students in the VDL. Analysis of the distributions of the anomaly measure A(x) confirmed the statistical significance of the proposed metric for distinguishing groups. The calibration curve demonstrated the adequacy of the model in reproducing the probabilities of belonging to the risk group. In general, the results obtained confirmed the correctness of the model and the mathematical apparatus selected for the study. The study of the dependence of the classification accuracy on the threshold value θ made it possible to determine the optimal cutoff level for the practical application of the model in the practice of using the VDL in higher education institutions. The theoretical value of the study lies in the development of methodological tools for proactive monitoring of educational activities in distance learning conditions. The practical value of the results obtained lies in the possibility of their implementation in existing distance learning systems for the tasks of early detection of students with signs of academic maladjustment and timely implementation of corrective measures.
Downloads
References
Buitrago-Ropero, M. E., Ramírez-Montoya, M. S., & Laverde, A. C. (2023). Digital footprints (2005–2019): A systematic mapping of studies in education. Interactive Learning Environments, 31(2), 876–889.
Nugumanova, A., & Baiburin, Y. (2019). Exploration of student behavior patterns through digital footprints. Journal of Mathematics, Mechanics and Computer Science, 103(3), 43–54.
Lakhno, V., Voloshyn, S., Mamchenko, S., Kulinich, O., & Kasatkin, D. (2024). Cluster analysis for studying digital footprints of students in educational institutions. Cybersecurity: Education, Science, Technique, 3(23), 31–41.
Klymenko, Ye. O. (2025). Development of information systems for predictive analytics of students’ academic performance. In O. Patriak et al. (Eds.), Information society: Technological, economic and technical aspects of development (Issue 98, pp. 22–24). Ternopil, Ukraine & Opole, Poland: NGO “Scientific Community”; WSZIA w Opolu; FOP Shpak V. B.
Appiah-Kubi, P., Zouhri, K., Basile, E., & McCabe, M. (2022). Analysis of engineering technology students’ digital footprints in synchronous and asynchronous blended courses. International Journal of Engineering Pedagogy, 12(1), 63–74.
Pichkur, M. O., Poluden, L. I., Demchenko, I. I., & Sotska, H. I. (2023). Monitoring digital footprints of fine arts training of higher art education students. Information Technologies and Learning Tools, 2(94), 128–149.
Lakhno, V., Kurbaiyazov, N., Lakhno, M., Kryvoruchko, O., Desiatko, A., Tsiutsiura, S., & Tsiutsiura, M. (2024). Analysis of digital footprints associated with cybersecurity behavior patterns of users of university information and education systems. International Journal of Electronics and Telecommunications, 673–682.
Karabatak, S., & Karabatak, M. (2020, June). Z generation students and their digital footprints. In 2020 8th International Symposium on Digital Forensics and Security (ISDFS) (pp. 1–5). IEEE.
Olipas, C. N. P. (2023). Exploring differences in demographic profiles and digital footprint awareness between private and public-school students: A comparative study. East Asian Journal of Multidisciplinary Research, 2(4), 1415–1436.
Rakow, K. E., Upsher, R. J., Foster, J. L., Byrom, N. C., & Dommett, E. J. (2023). Student perspectives on their digital footprint in virtual learning environments. Frontiers in Education, 8, Article 1208671.
Scanlon, P. (2018). Using students’ digital footprints to identify peer influences on academic outcomes (Doctoral dissertation, Dublin City University).
Evcimen, F. D., & Öteleş, E. Ü. U. (2025). The effect of critical thinking practices on digital footprint. Problems of Education in the 21st Century, 83(3), 306–318.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Альона Десятко, Євгеній Нікітенко, Валерій Гладких
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
