Document Open Access Logo

Immersive Pedagogy: Converting AI-Driven Podcasts into Virtual Reality Learning Objects

Authors Tomas Blažauskas , Eglė Butkevičiūtė , Filippo Sanfilippo , Patrikas Armalis , Ugnė Auksoraitytė

PDF HTML 5

Files

Thumbnail PDF
PDF
OASIcs.ICPEC.2025.16.pdf
  • Filesize: 2.13 MB
  • 12 pages
HTML5 Logo HTML (experimental)
OASIcs.ICPEC.2025.16.html

Document Identifiers

Subject Classification

ACM Subject Classification
  • Software and its engineering → General programming languages
Keywords
  • Artificial Intelligence
  • Virtual Reality
  • NotebookLB
  • Learning objects
  • content generation

Metrics

Abstract

Educational content creation is being transformed by artificial intelligence (AI) tools that can generate, process, and deliver learning materials across different environments. This paper presents a novel approach for converting AI-generated podcasts into immersive virtual reality (VR) learning experiences. We use the NotebookLM platform to create educational podcast audio recordings, which are then transformed into VR learning objects through automatic transcription, speaker diarization, and integration into a VR environment. The resulting VR learning objects address multiple learning preferences - supporting auditory learners through audio and visual learners through virtual presenters, and kinesthetic learners through immersive interaction. We evaluated this approach within a software engineering course, demonstrating its practical applicability and educational effectiveness.

Cite As Get BibTex

Tomas Blažauskas, Eglė Butkevičiūtė, Filippo Sanfilippo, Patrikas Armalis, and Ugnė Auksoraitytė. Immersive Pedagogy: Converting AI-Driven Podcasts into Virtual Reality Learning Objects. In 6th International Computer Programming Education Conference (ICPEC 2025). Open Access Series in Informatics (OASIcs), Volume 133, pp. 16:1-16:12, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025) https://doi.org/10.4230/OASIcs.ICPEC.2025.16

Author Details

Tomas Blažauskas
  • Department of Software Engineering, Kaunas University of Technology, Lithuania
Eglė Butkevičiūtė
  • Department of Software Engineering, Kaunas University of Technology, Lithuania
Filippo Sanfilippo
  • Department of Software Engineering, Kaunas University of Technology, Lithuania
Patrikas Armalis
  • Department of Software Engineering, Kaunas University of Technology, Lithuania
Ugnė Auksoraitytė
  • Department of Software Engineering, Kaunas University of Technology, Lithuania

Funding

This research was funded by the Erasmus programme under the grant number 2023-1-ES01-KA220-VET-000153652.

Acknowledgements

We want to thank all partners from the VR4INCLUSIVE Erasmus project whose contribution made this article possible.

References

  1. Saadia Ayub, Asiya Karim, and Amina Laraib. Learning styles of medical students. The Professional Medical Journal, 30(09):1214-1218, 2023. URL: https://doi.org/10.29309/TPMJ/2023.30.09.7650.
  2. Aaron Bangor, Philip T. Kortum, and James T. Miller. Determining what individual sus scores mean: Adding an adjective rating scale. Journal of Usability Studies, 4(3):114-123, 2009. Google Scholar
  3. John Brooke. SUS - a quick and dirty usability scale, pages 189-194. Taylor and Francis, January 1996. Google Scholar
  4. R.V. Mahendra Gowda. Education 5.0: Evolution of promising digital technologies - a comprehensive review. International Journal of Advanced Science and Engineering, 10(2):3442-3448, 2023. URL: https://doi.org/10.29294/ijase.10.2.2023.3422-3448.
  5. Peter Henderson, Xuechen Li, Dan Jurafsky, Tatsunori Hashimoto, Mark A Lemley, and Percy Liang. Foundation models and fair use. Journal of Machine Learning Research, 24(400):1-79, 2023. Google Scholar
  6. Robin Kay. Evaluating learning, design, and engagement in web-based learning tools (wblts): The wblt evaluation scale. COMPUTERS IN HUMAN BEHAVIOR, 27(5):1849-1856, September 2011. URL: https://doi.org/10.1016/j.chb.2011.04.007.
  7. Subhankar Maity and Aniket Deroy. Generative ai and its impact on personalized intelligent tutoring systems. arXiv preprint arXiv:2410.10650, 2024. URL: https://doi.org/10.35542/osf.io/kawr5.
  8. Kazunori Matsumoto. Exploring patterns of generative ai utilization in education. IIAI Letters on Informatics and Interdisciplinary Research, 4, 2023. URL: https://doi.org/10.52731/liir.v004.134.
  9. A. Pérez, G. Garcés Díaz-Muniõ, A. Giménez, J. A. Silvestre-Cerdà, A. Sanchis, J. Civera, M. Jiménez, C. Turró, and A. Juan. Towards cross-lingual voice cloning in higher education. Engineering Applications of Artificial Intelligence, 105:104413, 2021. URL: https://doi.org/10.1016/j.engappai.2021.104413.
  10. Jeff Sauro and Jim Lewis. How to interpret a sus score, 2023. Accessed: 2025-05-17. URL: https://measuringu.com/interpret-sus-score/.
  11. Peilin Wu. Beyond audio: Advancing speaker diarization with text-based methodologies and comprehensive evaluation. Honors thesis, Emory University, 2024. URL: https://etd.library.emory.edu/concern/etds/rb68xd387.
  12. T. Xu, Y. Liu, Y. Jin, Y. Qu, J. Bai, W. Zhang, and Y. Zhou. From recorded to ai‐generated instructional videos: A comparison of learning performance and experience. British Journal of Educational Technology, 2024. URL: https://doi.org/10.1111/bjet.13530.
  13. Z. Yin, Y. Wang, T. Papatheodorou, and P. Hui. Text2vrscene: Exploring the framework of automated text-driven generation system for vr experience. In IEEE Conference on Virtual Reality and 3D User Interfaces (VR), pages 701-711, 2024. URL: https://doi.org/10.1109/VR58804.2024.00090.
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact