Real Time Digital Twin Framework for Big Data-Driven Online Education Ecosystem
DOI:
https://doi.org/10.4108/eetsis.11312Keywords:
Digital Twin, Online Education, Big Data Analytics, Real-Time Monitoring, Student Behavior Prediction, Personalized LearningAbstract
INTRODUCTION: The rapid expansion of online education platforms has created unprecedented opportunities for personalized learning but also presents challenges in monitoring student engagement, learning outcomes, and instructional quality in real-time.
OBJECTIVES: This research proposes a real-time digital twin framework for a big data-driven online education ecosystem, designed to continuously capture and analyze large-scale educational data that enhances learning and teaching effectiveness.
METHODS: The digital twin online learning dataset with 345 students is obtained. The obtained data are preprocessed by the data cleaning for removing duplicate entries and z-score normalization to normalize the numerical features in the dataset. By integrating big data analytics and Deep Learning (DL) techniques based on an Adaptive Monarch Butterfly Optimized Graph convolutional with Long Short-Term Memory (AMB-GC-LSTM) that combines Long Short-Term Memory (LSTM) networks for sequential student behavior prediction and Graph Convolutional Networks (GCNs) for modeling collaborative learning relationships, the system enables accurate prediction of student engagement, performance trends, and early identification of at-risk learners.
RESULTS: The AMB is employed to optimize the GC-LSTM parameters for higher accuracy and cost computation reduction. Experimental evaluation demonstrates that the digital twin-driven ecosystem improves engagement, learning outcomes, and teaching efficiency.
CONCLUSION: Comparison results provide an enhanced accuracy (0.965), precision (0.945), recall (0.974), and F1-score (0.959) with the Python implementation. This research presents a novel approach for integrating digital twin technology, big data analytics, and deep learning to create an intelligent, responsive, and scalable online education ecosystem capable of supporting continuous improvement in teaching and learning.
References
[1] Zhou B. Building a smart education ecosystem from a metaverse perspective. Mob Inf Syst. 2022;2022(1):1938329. https://doi.org/10.1155/2022/1938329
[2] Nguyen LT, Tuamsuk K. Digital learning ecosystem at educational institutions: A content analysis of scholarly discourse. Cogent Educ. 2022;9(1):2111033. https://doi.org/10.1080/2331186X.2022.2111033
[3] Sheng D, Wang Y. Design of innovation and entrepreneurship education ecosystem in universities based on user experience. Math Probl Eng. 2022;2022(1):3266326. https://doi.org/10.1155/2022/3266326
[4] Pardo-Baldoví MI, San Martín-Alonso Á, Peirats-Chacón J. The smart classroom: Learning challenges in the digital ecosystem. Educ Sci. 2023;13(7):662. https://doi.org/10.3390/educsci13070662
[5] Siddiq F, Olofsson AD, Lindberg JO, Tomczyk L. What will be the new normal? Digital competence and 21st-century skills. Educ Inf Technol. 2024;29(6):7697–7705. https://doi.org/10.1007/s10639-023-12067-y
[6] Shu D, Yang S, Sato M. Cultivating a new ecosystem in English language teaching. Mod Lang J. 2023;107(2):405–427. https://doi.org/10.1111/modl.12847
[7] Alam A, Mohanty A. Integrated constructive robotics in education (ICRE) model: A paradigmatic framework. Cogent Educ. 2024;11(1):2324487. https://doi.org/10.1080/2331186X.2024.2324487
[8] Ilic P. Reducing the impact of emergency remote teaching through personal digital ecosystems. IEEE Trans Educ. 2024;67(3):336–342. https://doi.org/10.1109/TE.2024.3368047
[9] Paradeda RB, Santos HVS. Factors negatively influencing students’ transition to emergency remote education. Comput Educ Open. 2022; 3:100098. https://doi.org/10.1016/j.caeo.2022.100098
[10] Degen K, Lutzens R, Beschorner P, Lucke U. Public education data at the crossroads. Electron Mark. 2025;35(1):19. https://doi.org/10.1007/s12525-024-00752-w
[11] Cam TA, Chung NHT. Impactful research fronts in the digital educational ecosystem. Front Educ. 2025; 10:1557812. https://doi.org/10.3389/feduc.2025.1557812
[12] Forkosh-Baruch A, Voogt J, Knezek G. Moving forward to new educational realities in the digital era. Technol Knowl Learn. 2024;29(4):1685–1691. https://doi.org/10.1007/s10758-024-09785-8
[13] Chen PKA. Influence of metaverse on building entrepreneurship education ecosystems. Eng Proc. 2025;103(1):3. https://doi.org/10.3390/engproc2025103003
[14] Aly M. Advanced facial expression recognition for real-time student tracking via deep learning. Multimed Tools Appl. 2025;84(13):12575–12614. https://doi.org/10.1007/s11042-024-19392-5
[15] Mao X. Online education quality assessment model based on deep learning. Discov Artif Intell. 2025;5(1):1–26. https://doi.org/10.1007/s44163-025-00421-7
[16] Li X, Zhang Y. Intrusion detection via deep learning in English online education. Alex Eng J. 2025; 124:582–590. https://doi.org/10.1016/j.aej.2025.03.051
[17] Zhou Q, Zhang H, Li F. Online interactive teaching and university students’ deep learning. Educ Sci. 2024;14(6):664. https://doi.org/10.3390/educsci14060664
[18] Masood JAIS, et al. Hybrid deep learning model to predict high-risk students in virtual environments. IEEE Access. 2024; 12:103687–103703. https://doi.org/10.1109/ACCESS.2024.3434644
[19] Alruwais NM, Zakariah M. Student recognition and activity monitoring in e-classes. IEEE Access. 2024; 12:66110–66128. https://doi.org/10.1109/ACCESS.2024.3354981
[20] Hussain T, Yu L, Asim M, Ahmed A, Wani MA. Enhancing e-learning adaptability using hybrid deep learning. Information. 2024;15(5):277. https://doi.org/10.3390/info15050277
[21] Wen X, Juan H. Early prediction of student performance using deep neural networks. Appl Sci. 2023;13(15):8933. https://doi.org/10.3390/app13158933
[22] Du H, Xing W, Pei B. Automatic text generation via deep learning for online learning communities. Interact Learn Environ. 2023;31(8):5021–5036. https://doi.org/10.1080/10494820.2021.1993932
[23] Pei Y, Lu G. Intelligent educational evaluation system using deep learning. IEEE Access. 2023; 11:29790–29799. https://doi.org/10.1109/ACCESS.2023.3260979
[24] Aly M, Ghallab A, Fathi IS. Enhancing facial expression recognition in online learning. IEEE Access. 2023; 11:121419–121433. https://doi.org/10.1109/ACCESS.2023.3325407
[25] Ren J, Wu S. Predicting user temporal interactions on online course platforms. Comput Educ Artif Intell. 2023; 4:100133. https://doi.org/10.1016/j.caeai.2023.100133
[26] AlZu’bi S, et al. Deep learning technique for detecting emotional impact in online education. Electronics. 2022;11(18):2964. https://doi.org/10.3390/electronics11182964
[27] Xu J, Liu Y, Liu J, Qu Z. Effectiveness of English online learning based on deep learning. Comput Intell Neurosci. 2022;2022(1):1310194. https://doi.org/10.1155/2022/1310194
[28] Zhou J. Deep learning-driven distributed communication for cluster online education. Int J Commun Syst. 2022;35(1):e5009. https://doi.org/10.1002/dac.5009
[29] Mubarak AA, Cao H, Zhang W. Prediction of early dropout in online learning. Interact Learn Environ. 2022;30(8):1414–1433. https://doi.org/10.1080/10494820.2020.1727529
[30] Wang X. Online education resource recommendation via deep learning. Comput Intell Neurosci. 2022;2022(1):3674271. https://doi.org/10.1155/2022/3674271
[31] Gudivaka BR. Designing AI-assisted music teaching with big data analysis. Curr Sci Humanit. 2021;9(4):1–14.
[32] Zhang Y. Intelligent edge caching and computing for scalable information systems. EAI Endorsed Trans Scalable Inf Syst. 2023;10(5).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yanyu Qian, Na Zhang
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
