ANALYSIS OF DIGITAL FOOTPRINTS AND IOT BEHAVIORAL DATA IN THE SMART CAMPUS

DOI: 10.31673/2409-7292.2026.010438

Abstract

The article proposes a mathematical model for analyzing digital traces (DST) of higher education students, focused on
the needs of modern Smart education as a component of the intellectual urban infrastructure, in particular Kyiv. The relevance
of the study is due to the increase in the emotional vulnerability of student youth in the conditions of the full-scale military
aggression of the Russian Federation against Ukraine, which caused systemic changes in the nature of digital communication,
the intensity of stress reactions and the stability of psycho-emotional states of higher education students. Taking into account
the multidirectional influence of these factors, the model proposed in the article integrated the probabilistic classification of the
tone of text messages in the digital educational environment, Bayesian updating of assessments, a network model of the diffusion
of emotions in the student community and behavioral IoT signals, which ultimately allowed for a comprehensive assessment of
the emotional variability of the digital educational environment. The study used data from artificial digital traces and behavioral
metrics typical of two higher education institutions in Kyiv, which made it possible to model realistic scenarios of changes in
emotional states in student networks of these HEIs. The results of the simulation experiment confirmed that text digital traces
are a relevant and informative source for detecting individual and group emotional fluctuations, in particular in situations of
increased anxiety associated with security threats. Adding an IoT component to the model significantly strengthened its
predictive properties. After all, behavioral factors, such as activity in the HEI's digital services, movement, and presence on
campus, reflect a significant impact on the stability or destabilization of the emotional states of education seekers. The proposed
model allowed to detect periods of increased tension not only by text messages, but also by behavioral patterns of users, which
makes it a useful tool for operational monitoring of the state of the student environment. The model is suitable for early detection
of potentially problematic situations in the interaction of applicants, supports management decision-making in HEIs and has the
potential for integration into Smart Campus systems. Taking into account the CS in combination with IoT data has opened up
new opportunities for the synthesis of systems to support the psycho-emotional well-being of higher education applicants, which
is relevant in conditions of war and high social instability of youth.
Keywords: digital traces, Smart education, Smart campus, IoT data, behavioral analytics, sentiment analysis, network
models, emotion diffusion, Bayesian updating, educational environment modeling.

References
1. Козубцова, Л., & Козубцов, І. (2024). Поняття і місце smart school в концепції інфраструктури SMART
CITY. TTSIIT, 68.
2. Мужанова, Т. М. (2017). «Розумне місто» як інноваційна модель управління. «Економіка. Менеджмент.
Бізнес» № 2 (20), 2017. 116-122.
3. Дзюндзюк, К. В. (2023). Публічне управління міським розвитком на засадах концепції розумного міста.
Дисертація на здобуття наукового ступеня доктора філософії за спеціальністю 281, публічне управління та
адміністрування. Харківський національний університет імені В.Н. Каразіна, Харків, 2023.
4. Алексов, С. В., & Дідик, А. В. (2023). Перспективи впровадження системи «розумний дім» у заклади
освіти. Трансформаційна економіка, (2 (02)), 5-9.
5. Чорненька, Ж. А., Грицюк, М. Я. І., & Бідучак, А. С. (2017). Впровадження SMART–освіти у вищих
навчальних закладах. The Scientific Heritage, (11-2 (11)), 63-65.
6. Лахно, В., Волошин, С., Мамченко, С., Кулініч, О., & Касаткін, Д. (2024). Кластерний аналіз для
дослідження цифрових слідів студентів закладів освіти. Електронне фахове наукове видання «Кібербезпека:
освіта, наука, техніка», 3(23), 31-41.
7. Das, N. (2023). Digital education as an integral part of a smart and intelligent city: a short review. Digital
learning based education: transcending physical barriers, 81-96.
8. Liang, H., Ganeshbabu, U., & Thorne, T. (2020). A dynamic Bayesian network approach for analysing topicsentiment evolution. IEEE Access, 8, 54164-54174.
9. Peralta, A. F., Kertész, J., & Iñiguez, G. (2022). Opinion dynamics in social networks: From models to data.
arXiv preprint arXiv:2201.01322.
10. Xu, H., Xu, M., Deng, X., & Wang, B. (2025). Sentiment Diffusion in Online Social Networks: A Survey from
the Computational Perspective. ACM Computing Surveys.
11. Mujahid, Muhammad, et al. "Sentiment analysis and topic modeling on tweets about online education during
COVID-19." Applied Sciences 11.18 (2021): 8438.
12. El Alaoui, I., Gahi, Y., Messoussi, R., Chaabi, Y., Todoskoff, A., & Kobi, A. (2018). A novel adaptable
approach for sentiment analysis on big social data. Journal of Big Data, 5(1), 1-18.
13. Chakraborty, K., Bhatia, S., Bhattacharyya, S., Platos, J., Bag, R., & Hassanien, A. E. (2020). Sentiment
Analysis of COVID-19 tweets by Deep Learning Classifiers-A study to show how popularity is affecting accuracy in
social media. Applied Soft Computing, 97, 106754.
14. Zhou, Lili. Optimisation design of distance education resource recommendation system based on hierarchical
linear model. International Journal of Continuing Engineering Education and Life Long Learning 32.6 (2022): 681-698.
15. Zhou, H., Jiang, S., & Liu, X. (2021). Regression analysis of intelligent education based on linear mixed effect
model. Journal of Ambient Intelligence and Humanized Computing, 1-13.