Shixian Zhou, Minghuan Shen, Xiaolin Wen, Zijun Qiu, Yongliang Jiang, Xiangyang Wu, Fei Wu, Yong Wang, Zhiguang Zhou — arXiv preprint (2026). 📄 Full text (arXiv)
Synthesis
SAVVY is an interactive visual analytics system for video-based learning that integrates visual and auditory attention signals from multimodal brain data to support top-down exploration of student attention variation across instructional videos.
A novel attention modeling framework based on multimodal brain signals enables stable tracking of student attention in real-world environments, addressing the noise susceptibility of existing attention quantification algorithms.
The system supports teachers in analyzing pilot cohorts' attention before releasing videos, reducing the guesswork of empirical revision by making attention patterns interpretable at scale.
The work connects AI-based attention estimation to instructional design practice, giving teachers an evidence base for when and where videos lose student engagement.
Related Pages
Citation
APA: Zhou, S., Shen, M., Wen, X., Qiu, Z., Jiang, Y., Wu, X., Wu, F., Wang, Y., & Zhou, Z. (2026). SAVVY: Student attention visualization for video-based learning analysis. arXiv:2607.29413.