SAVVY: Student Attention Visualization for Video-based Learning Analysis

Shixian Zhou, Minghuan Shen, Xiaolin Wen, Zijun Qiu, Yongliang Jiang, Xiangyang Wu, Fei Wu, Yong Wang, Zhiguang Zhou — arXiv preprint (2026).

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.

Connected Concepts

Connected Articles

Physiological Signals Exam Outcomes ML — Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning

Wordstream Glass Learning Analytics — Through the WordStream Glass: Revisiting Quantitative Encoding for Qualitative Learning Analytics

Hypergamification Game Engine LMS — Hypergamigication Through Integrating Game Engines and Learning Management Systems: Ender's Game

GenAI Tutor Engagement Patterns — Not All Students Engage Alike: Multi-Institution Patterns in GenAI Tutor Use

A4l Analytics Pipeline — Generalizing a Highly Configurable Analytics Pipeline to Replicate and Support Educational Research Across Multiple Domains

LLM Sentiment Analysis Education Research — LLM-assisted sentiment analysis for integrated computational and qualitative mixed methods education research: A case study of students' written reflection assignments

Citation

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.