SAVVY: Student Attention Visualization for Video-based Learning Analysis

2026-07-30

AI Summary

This work addresses the limitations of existing methods for quantifying student attention in video-based learning, which are often susceptible to environmental noise and insufficiently support instructors in refining instructional content. To overcome these challenges, the authors propose a multimodal attention modeling framework that integrates neurophysiological signals with multilevel course information, accompanied by SAVVY—an interactive visual analytics system. SAVVY fuses audiovisual attention cues to enable attention trajectory tracking and attribution analysis across multiple temporal granularities, empowering educators to explore student attention dynamics from a top-down perspective. The effectiveness and usability of SAVVY in detecting attention fluctuations and facilitating the optimization of instructional videos are validated through quantitative experiments, case studies, and expert interviews.

Abstract

Video-Based Learning (VBL) has become a popular delivery medium of education in the past decade, ranging from online education to hybrid learning. Students' rising expectations for video quality have motivated teachers to enhance the design of instructional videos before releasing them. Analyzing the attention of pilot cohorts in advance has become a conventional optimization strategy to guide course improvement. However, existing attention quantification algorithms are highly susceptible to noise in real-world environments, degrading estimation accuracy. Moreover, even when attention data are available, teachers must still invest substantial effort in empirical revision attempts, limiting practical feasibility. To address these challenges, we first propose a novel attention modeling framework based on multimodal brain signals that enables stable tracking of student attention levels. We then develop SAVVY, a novel interactive visual analytics system that integrates visual and auditory attention to support top-down exploration of student attention variations. SAVVY comprises three coordinated visualization modules. These modules incorporate multi-level information, including course content structure, audiovisual information density, and attentional resource allocation, and provide multi-temporal-resolution attention trajectories of individual students, enabling teachers to comprehensively analyze the underlying causes of attention fluctuations and inform their subsequent instructional video improvement. We evaluate SAVVY through quantitative experiments, two case studies, and expert interviews. The results demonstrate the effectiveness and usability of SAVVY in intuitively identifying student attention variations and supporting instructional video optimization.

Problem

• Video-Based Learning
• Student Attention
• Attention Quantification
• Instructional Video Optimization
• Visual Analytics

Innovation

• multimodal brain signals
• attention modeling
• visual analytics
• video-based learning
• interactive visualization