Abstract
This research proposes a deep neural network architecture for detecting focal periods for online students in lecture archives. Due to the COVID-19 pandemic, most universities attempted to use online education instead of traditional classrooms. However, watching long lecture archives, just recorded face-to-face lectures, is difficult for students to keep their attention. Hence, how to provide focal periods of the lecture archives is essential to maintain educational effectiveness in such a situation. This research divides lecture archives with high quality and fixed camera angles into 1-min segments, counts how many times students have accessed each segment from LMS as the label data, and defines the students’ focal periods. Then, we demonstrated deep neural network architectures with the combined features to improve detection reliability. Our experiments showed that the proposed method could detect the focal periods with 56.8% accuracy. Although there is room for improvement in accuracy, this enables us to detect certain focal periods with a small amount of computation without using semantic features.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Guo, P.J., Kim, J., Rubin, R.: How video production affects student engagement: an empirical study of mooc videos. In Proceedings of the first ACM Conference on Learning@ Scale Conference, pp. 41–50 (2014)
Andra, M.B., Usagawa, T.: Automatic lecture video content summarization with attention-based recurrent neural network. In: 2019 International Conference of Artificial Intelligence and Information Technology (ICAIIT), pp. 54–59. IEEE (2019)
Zhang, J., Bourguet, M.-L., Venture, G.: The effects of video instructor’s body language on students’ distribution of visual attention: An eye-tracking study. In: Proceedings of the 32nd International BCS Human Computer Interaction Conference 32, pp. 1–5 (2018)
Wyse, L.: Audio spectrogram representations for processing with convolutional neural networks. In: Proceedings of the First International Workshop on Deep Learning and Music Joint with IJCNN, vol. 1(1), pp. 37–41 (2017)
Slykhuis, D.A., Wiebe, E.N., Annetta, L.A.: Eye-tracking students’ attention to powerpoint photographs in a science education setting. J. Sci. Educ. Technol. 14(5), 509–520 (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Sheng, R., Ota, K., Hasegawa, S. (2022). An Automatic Focal Period Detection Architecture for Lecture Archives. In: Rodrigo, M.M., Matsuda, N., Cristea, A.I., Dimitrova, V. (eds) Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium. AIED 2022. Lecture Notes in Computer Science, vol 13356. Springer, Cham. https://doi.org/10.1007/978-3-031-11647-6_71
Download citation
DOI: https://doi.org/10.1007/978-3-031-11647-6_71
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11646-9
Online ISBN: 978-3-031-11647-6
eBook Packages: Computer ScienceComputer Science (R0)