Utilizing Google NotebookLM in Teaching and Research at Ho Chi Minh City University of Physical Education and Sports
DOI:
https://doi.org/10.65150/EP-jsshrs/V2E7/2026-01Keywords:
Generative Artificial Intelligence, NotebookLM, Higher Education, Educational Technology, Retrieval-Augmented GenerationAbstract
The Fourth Industrial Revolution and the unprecedented proliferation of Generative Artificial Intelligence (AI) have catalyzed a profound transformation within the global higher education landscape. Specialized academic institutions, particularly those focusing on interdisciplinary fields such as pedagogical theory and movement science, are confronting significant challenges associated with digital transformation and information overload. This research critically examines the application of Google NotebookLM—an advanced, Retrieval-Augmented Generation (RAG)-based language model—in optimizing teaching methodologies and scientific research workflows at Ho Chi Minh City University of Physical Education and Sports (UPES). Unlike conventional large language models that are prone to algorithmic “hallucinations,” NotebookLM leverages an expansive context window and strict data grounding to ensure high academic integrity and transparent citation mechanisms. Through a comprehensive conceptual analysis drawing upon contemporary educational technology frameworks, this paper explores the platform’s multimodal pedagogical capabilities, notably the Audio Overview feature, which facilitates dynamic, dialogue-based learning tailored to diverse cognitive preferences. Furthermore, the study outlines a systematic, four-step methodological workflow for researchers to streamline literature reviews. Concurrently, it provides a rigorous epistemological critique of the tool’s intrinsic limitations, specifically addressing intellectual property vulnerabilities, the potential erosion of proactive cognitive engagement, and the risks of algorithmic bias stemming from frequency heuristics. Ultimately, this paper proposes strategic recommendations for cultivating an “Active Learning Ecosystem” and optimizing academic literature syntheses, thereby contributing to the comprehensive digital transformation objectives at UPES in the era of artificial intelligence.
References
1) Baker, T., & Smith, L. (2019). Educ-AI-tion rebooted? Exploring the future of artificial intelligence in schools and colleges. Nesta. https://media.nesta.org.uk/documents/Future_of_AI_and_education_v5_WEB.pdf
2) Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610–623. https://doi.org/10.1145/3442188.3445922
3) Crompton, H., & Burke, D. (2023). Artificial intelligence in higher education: The state of the field. International Journal of Educational Technology in Higher Education, 20(1), Article 22. https://doi.org/10.1186/s41239-023-00392-8
4) Google. (2023). Introducing NotebookLM. Google Blog. https://blog.google/technology/ai/notebooklm-google-ai/
5) Mollick, E., & Mollick, L. (2024). Instructors as innovators: A future-focused approach to new AI learning opportunities, with prompts (Wharton School Research Paper No. 4802463). SSRN Electronic Journal. http://dx.doi.org/10.2139/ssrn.4802463
6) UNESCO. (2024). Guidance for generative AI in education and research. UNESCO Publishing. https://unesdoc.unesco.org/ark:/48223/pf0000386693
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Phan Thanh Viet (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.









