Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Analysis, Modeling and Design of Personalized Digital Learning Environment (2405.10476v1)

Published 17 May 2024 in cs.HC, cs.AI, and cs.SE

Abstract: This research analyzes, models and develops a novel Digital Learning Environment (DLE) fortified by the innovative Private Learning Intelligence (PLI) framework. The proposed PLI framework leverages federated machine learning (FL) techniques to autonomously construct and continuously refine personalized learning models for individual learners, ensuring robust privacy protection. Our approach is pivotal in advancing DLE capabilities, empowering learners to actively participate in personalized real-time learning experiences. The integration of PLI within a DLE also streamlines instructional design and development demands for personalized teaching/learning. We seek ways to establish a foundation for the seamless integration of FL into learning systems, offering a transformative approach to personalized learning in digital environments. Our implementation details and code are made public.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. P. Brusilovsky, “AI in education, learner control, and human-ai collaboration,” International Journal of Artificial Intelligence in Education, pp. 1–14, 2023.
  2. D. Roldán-Álvarez and F. J. Mesa, “Intelligent deep-learning tutoring system to assist instructors in programming courses,” IEEE Transactions on Education, vol. 67, no. 1, pp. 153–161, 2024.
  3. F. Fruett, F. P. Barbosa, S. C. Z. Fraga, and P. I. A. Guimarães, “Empowering steam activities with artificial intelligence and open hardware: The bitdoglab,” IEEE Transactions on Education, pp. 1–10, 2024.
  4. L. Zhang, J. D. Basham, and S. Yang, “Understanding the implementation of personalized learning: A research synthesis,” Educational Research Review, vol. 31, p. 100339, 2020.
  5. N. Yannier, S. E. Hudson, H. Chang, and K. R. Koedinger, “AI adaptivity in a mixed-reality system improves learning,” International Journal of Artificial Intelligence in Education, pp. 1–18, 2024.
  6. L. Aroyo, P. Dolog, G.-J. Houben, M. Kravcik, A. Naeve, M. Nilsson, and F. Wild, “Interoperability in personalized adaptive learning,” Journal of Educational Technology & Society, vol. 9, no. 2, pp. 4–18, 2006.
  7. L. E. Lwakatare, A. Raj, I. Crnkovic, J. Bosch, and H. H. Olsson, “Large-scale machine learning systems in real-world industrial settings: A review of challenges and solutions,” Information and software technology, vol. 127, p. 106368, 2020.
  8. L. Tetzlaff, F. Schmiedek, and G. Brod, “Developing personalized education: A dynamic framework,” Educational Psychology Review, vol. 33, pp. 863–882, 2021.
  9. E. Ameloot, R. Tijs, A. Thomas, B. Rienties, and T. Schellens, “Supporting students’ basic psychological needs and satisfaction in a blended learning environment through learning analytics,” Computers & Education, p. 104949, 2023.
  10. R. E. Mayer, “Multimedia instruction,” Handbook of research on educational communications and technology, pp. 385–399, 2014.
  11. C. Armatas, D. Holt, and M. Rice, “Impacts of an online-supported, resource-based learning environment: Does one size fit all?,” Distance education, vol. 24, no. 2, pp. 141–158, 2003.
  12. U. Maier and C. Klotz, “Personalized feedback in digital learning environments: Classification framework and literature review,” Computers and Education: Artificial Intelligence, vol. 3, p. 100080, 2022.
  13. L. P. Macfadyen and S. Dawson, “Mining lms data to develop an “early warning system” for educators: A proof of concept,” Computers & education, vol. 54, no. 2, pp. 588–599, 2010.
  14. S. C. Matz and O. Netzer, “Using big data as a window into consumers’ psychology,” Current opinion in behavioral sciences, vol. 18, pp. 7–12, 2017.
  15. S. Aheleroff, N. Mostashiri, X. Xu, and R. Y. Zhong, “Mass personalisation as a service in industry 4.0: A resilient response case study,” Advanced Engineering Informatics, vol. 50, p. 101438, 2021.
  16. F. Bashir and N. F. Warraich, “Systematic literature review of semantic web for distance learning,” Interactive Learning Environments, vol. 31, no. 1, pp. 527–543, 2023.
  17. A. H. Duin and J. Tham, “The current state of analytics: Implications for learning management system (lms) use in writing pedagogy,” Computers and Composition, vol. 55, p. 102544, 2020.
  18. S. Montalvo, J. Palomo, and C. de la Orden, “Building an educational platform using nlp: A case study in teaching finance.,” J. Univers. Comput. Sci., vol. 24, no. 10, pp. 1403–1423, 2018.
  19. N. Matsuda, W. Weng, and N. Wall, “The effect of metacognitive scaffolding for learning by teaching a teachable agent,” International Journal of Artificial Intelligence in Education, vol. 30, pp. 1–37, 2020.
  20. E. Gomede, R. M. de Barros, and L. de Souza Mendes, “Deep auto encoders to adaptive e-learning recommender system,” Computers and education: Artificial intelligence, vol. 2, p. 100009, 2021.
  21. C. A. Carver, R. A. Howard, and W. D. Lane, “Enhancing student learning through hypermedia courseware and incorporation of student learning styles,” IEEE transactions on Education, vol. 42, no. 1, pp. 33–38, 1999.
  22. B. Yang, H. Tang, L. Hao, and J. R. Rose, “Untangling chaos in discussion forums: A temporal analysis of topic-relevant forum posts in moocs,” Computers & Education, vol. 178, p. 104402, 2022.
  23. L. K. Fryer, M. Ainley, A. Thompson, A. Gibson, and Z. Sherlock, “Stimulating and sustaining interest in a language course: An experimental comparison of chatbot and human task partners,” Computers in Human Behavior, vol. 75, pp. 461–468, 2017.
  24. S. Minn, “Ai-assisted knowledge assessment techniques for adaptive learning environments,” Computers and Education: Artificial Intelligence, vol. 3, p. 100050, 2022.
  25. H. Khiat and S. Vogel, “A self-regulated learning management system: Enhancing performance, motivation and reflection in learning,” Journal of University Teaching & Learning Practice, vol. 19, no. 2, pp. 43–59, 2022.
  26. P. Prinsloo, S. Slade, and M. Khalil, “Student data privacy in moocs: A sentiment analysis,” Distance Education, vol. 40, no. 3, pp. 395–413, 2019.
  27. C.-H. Liao and J.-Y. Wu, “Deploying multimodal learning analytics models to explore the impact of digital distraction and peer learning on student performance,” Computers & Education, vol. 190, p. 104599, 2022.
  28. O. Tapalova and N. Zhiyenbayeva, “Artificial intelligence in education: Aied for personalised learning pathways.,” Electronic Journal of e-Learning, vol. 20, no. 5, pp. 639–653, 2022.
  29. D. Xu and H. Wang, “Intelligent agent supported personalization for virtual learning environments,” Decision Support Systems, vol. 42, no. 2, pp. 825–843, 2006.
  30. M. Z. Iqbal and A. G. Campbell, “Real-time hand interaction and self-directed machine learning agents in immersive learning environments,” Computers & Education: X Reality, vol. 3, p. 100038, 2023.
  31. C. Diwan, S. Srinivasa, G. Suri, S. Agarwal, and P. Ram, “Ai-based learning content generation and learning pathway augmentation to increase learner engagement,” Computers and Education: Artificial Intelligence, vol. 4, p. 100110, 2023.
  32. X. Weng and T. K. Chiu, “Instructional design and learning outcomes of intelligent computer assisted language learning: Systematic review in the field,” Computers and Education: Artificial Intelligence, p. 100117, 2023.
  33. U. Bezirhan and M. von Davier, “Automated reading passage generation with openai’s large language model,” arXiv preprint arXiv:2304.04616, 2023.
  34. C.-P. Dai and F. Ke, “Educational applications of artificial intelligence in simulation-based learning: A systematic mapping review,” Computers and Education: Artificial Intelligence, p. 100087, 2022.
  35. C.-P. Dai, F. Ke, Y. Pan, and Y. Liu, “Exploring students’ learning support use in digital game-based math learning: A mixed-methods approach using machine learning and multi-cases study,” Computers & Education, vol. 194, p. 104698, 2023.
  36. K. S. McCarthy, A. D. Likens, A. M. Johnson, T. A. Guerrero, and D. S. McNamara, “Metacognitive overload!: Positive and negative effects of metacognitive prompts in an intelligent tutoring system,” International Journal of Artificial Intelligence in Education, vol. 28, pp. 420–438, 2018.
  37. G.-J. Hwang, H.-Y. Sung, S.-C. Chang, and X.-C. Huang, “A fuzzy expert system-based adaptive learning approach to improving students’ learning performances by considering affective and cognitive factors,” Computers and Education: Artificial Intelligence, vol. 1, p. 100003, 2020.
  38. S. C. Tan, A. V. Y. Lee, and M. Lee, “A systematic review of artificial intelligence techniques for collaborative learning over the past two decades,” Computers and Education: Artificial Intelligence, p. 100097, 2022.
  39. A. Gulz, L. Londos, and M. Haake, “Preschoolers’ understanding of a teachable agent-based game in early mathematics as reflected in their gaze behaviors–an experimental study,” International Journal of Artificial Intelligence in Education, vol. 30, pp. 38–73, 2020.
  40. A. W. Li, “Using peerceptiv to support ai-based online writing assessment across the disciplines,” Assessing Writing, vol. 57, p. 100746, 2023.
  41. A. Y. Huang, O. H. Lu, and S. J. Yang, “Effects of artificial intelligence–enabled personalized recommendations on learners’ learning engagement, motivation, and outcomes in a flipped classroom,” Computers & Education, vol. 194, p. 104684, 2023.
  42. L. Meng, W. Zhang, Y. Chu, and M. Zhang, “Ld–lp generation of personalized learning path based on learning diagnosis,” IEEE Transactions on Learning Technologies, vol. 14, no. 1, pp. 122–128, 2021.
  43. A. Bhutoria, “Personalized education and artificial intelligence in the united states, china, and india: A systematic review using a human-in-the-loop model,” Computers and Education: Artificial Intelligence, vol. 3, p. 100068, 2022.
  44. A. Gandhi, K. Adhvaryu, S. Poria, E. Cambria, and A. Hussain, “Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions,” Information Fusion, vol. 91, pp. 424–444, 2023.
  45. X. Chen, H. Xie, D. Zou, and G.-J. Hwang, “Application and theory gaps during the rise of artificial intelligence in education,” Computers and Education: Artificial Intelligence, vol. 1, p. 100002, 2020.
  46. Y. Y. Mun and Y. Hwang, “Predicting the use of web-based information systems: self-efficacy, enjoyment, learning goal orientation, and the technology acceptance model,” International journal of human-computer studies, vol. 59, no. 4, pp. 431–449, 2003.
  47. W. Y. B. Lim, N. C. Luong, D. T. Hoang, Y. Jiao, Y.-C. Liang, Q. Yang, D. Niyato, and C. Miao, “Federated learning in mobile edge networks: A comprehensive survey,” IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 2031–2063, 2020.
  48. E. Marchiori, S. de Haas, S. Volnov, R. Falcon, R. Pinto, and M. Zamarato, “Android private compute core architecture,” arXiv preprint arXiv:2209.10317, 2022.
  49. N. Truong, K. Sun, S. Wang, F. Guitton, and Y. Guo, “Privacy preservation in federated learning: An insightful survey from the gdpr perspective,” Computers & Security, vol. 110, p. 102402, 2021.
  50. Y. Bellarhmouch, A. Jeghal, H. Tairi, and N. Benjelloun, “A proposed architectural learner model for a personalized learning environment,” Education and Information Technologies, vol. 28, no. 4, pp. 4243–4263, 2023.
  51. C. Mutimukwe, O. Viberg, L.-M. Oberg, and T. Cerratto-Pargman, “Students’ privacy concerns in learning analytics: Model development,” British Journal of Educational Technology, vol. 53, no. 4, pp. 932–951, 2022.
  52. N. S. Xin, A. S. Shibghatullah, M. H. Abd Wahab, et al., “A systematic review for online learning management system,” in Journal of Physics: Conference Series, vol. 1874, p. 012030, IOP Publishing, 2021.
  53. N. Dehbozorgi and M. T. Kunuku, “Exploring the influence of emotional states in peer interactions on students’ academic performance,” IEEE Transactions on Education, pp. 1–8, 2023.
  54. T. S. Brisimi, R. Chen, T. Mela, A. Olshevsky, I. C. Paschalidis, and W. Shi, “Federated learning of predictive models from federated electronic health records,” International journal of medical informatics, vol. 112, pp. 59–67, 2018.
  55. S. R. Pokhrel and J. Choi, “Federated learning with blockchain for autonomous vehicles: Analysis and design challenges,” IEEE Transactions on Communications, vol. 68, no. 8, pp. 4734–4746, 2020.
  56. K. D. Duy, T. Noh, S. Huh, and H. Lee, “Confidential machine learning computation in untrusted environments: A systems security perspective,” IEEE Access, vol. 9, pp. 168656–168677, 2021.

Summary

  • The paper presents a novel PLI framework that leverages federated learning to construct personalized models with enhanced privacy safeguards.
  • It employs a four-stage iterative process combining local model training and federation services to optimize digital learning experiences.
  • The research demonstrates significant improvements in learner performance prediction and establishes a decentralized approach to secure personalization.

Analysis, Modeling and Design of Personalized Digital Learning Environment

The paper "Analysis, Modeling and Design of Personalized Digital Learning Environment" by Sanjaya Khanal and Shiva Raj Pokhrel, proposes an innovative approach to enhancing digital learning environments (DLE) through the integration of a novel Private Learning Intelligence (PLI) framework. This framework leverages federated learning (FL) to autonomously construct personalized learning models for individual learners, significantly augmenting privacy protection and user engagement.

Summary of the Research

This research introduces the PLI framework that integrates FL techniques to develop and continuously refine personalized learning models while ensuring robust privacy safeguards. The PLI framework addresses the necessity for real-time personalization in DLEs and empowers learners by actively involving them in personalized learning experiences. The objectives are multifold: to streamline instructional design, reduce development demands for personalized teaching/learning, and establish a foundation for integrating FL into educational systems.

Three primary proof-of-concept designs within the PLI framework are explored:

  1. Virtual Intelligent Agents (VIPs)
  2. Learner Content Co-creation and Curation Tools (LCTs)
  3. Automated Self-Assessment and Feedback Tools (ASFs)

Methodology and Architecture

The methodology for implementing the PLI framework involves a structured four-stage iterative process. This process consists of enhancing FL for privacy assurance, securing local model training, improving collaborative systems, and optimizing performance through real-time monitoring and testing. The architecture of the PLI framework is composed of several integral components:

  1. PLI Framework: Governs the system, including algorithms and protocols for personalization.
  2. Local Model Training System (LMTS): Facilitates local, on-device training using datasets tailored to individual learners.
  3. Federation Services Hub: Coordinates interactions between local models and the global network ensuring that knowledge sharing respects privacy constraints.
  4. Network ML Servers: Aggregates updates from various PLIs and refines the global model.

By implementing a sandboxed environment and processing all computations locally, the PLI framework minimizes data privacy concerns while enabling advanced personalized learning features.

Numerical Results and Claims

The implementation details, including the code for the PLI framework, are made publicly available on GitHub, demonstrating the practical applications of the framework. The research claims that employing local model training augmented by FL offers robust privacy protection, contrary to traditional centralized models which pose significant privacy risks.

Strong numerical results from the research underscore the utility of the PLI framework. Using logistic regression models for testing, the paper highlighted significant improvement in predicting learner performance based on meticulously tracked learning behaviors and metrics such as login frequency, time spent, page visits, and quiz performance.

Implications and Future Developments

The practical implications of the PLI framework are profound. By decentralizing data processing and enhancing personalization, PLI ensures secure, individualized learning experiences. This not only optimizes the learning process but also alleviates common concerns surrounding user data privacy. Moreover, integrating FL into DLEs encourages the continuous development of models that adapt to evolving educational needs while maintaining privacy.

From a theoretical perspective, the PLI framework contributes to the evolving discourse on the interplay between personalization and privacy in educational technology. It challenges traditional paradigms by advocating for decentralized learning models and emphasizes the viability of FL in maintaining user confidentiality.

Future Directions

Future research avenues entail refining the PLI framework to incorporate advanced data sources such as sensor data from smartphones and wearable devices for an even more nuanced understanding of learner behavior. Further advancements could involve exploring the emotional and cognitive states of learners to provide a truly holistic personalized learning experience. Additionally, the integration of human expert oversight and differential privacy techniques could also bolster the credibility and accuracy of the system.

In conclusion, the PLI framework offers a comprehensive solution to the dual challenges of privacy and personalization in digital learning environments. By leveraging FL, the framework ensures that learners benefit from tailored educational experiences while maintaining robust privacy safeguards, indicating a significant step forward in the evolution of educational technology.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets