Skip to content

SAVVY content-derived visual and auditory information density metrics

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

Grounded in the Limited Capacity Model of Motivated Mediated Message Processing (LC4MP), SAVVY quantifies information density of both visual and auditory channels per slide-transition-induced event segment. Visual density combines edge density of image regions (detected with Mask R-CNN), average normalized IDF surprisal of slide text (detected with DBNet), weighted by region area ratios; auditory density uses the entropy of the narration's word distribution divided by narration duration, plus semantic similarity between slide text and transcript to capture cross-channel redundancy. The authors caution these are "content-derived proxy indicators" describing the presented content itself, not learners' internal cognitive states.

Accounts

  • Content-derived visual and auditory information density metrics grounded in LC4MP: Grounded in the Limited Capacity Model of Motivated Mediated Message Processing (LC4MP), SAVVY quantifies information density of both visual and auditory channels per slide-transition-induced event segment. Visual density combines edge density of image regions (detected with Mask R-CNN), average normalized IDF surprisal of slide text (detected with DBNet), weighted by region area ratios; auditory density uses the entropy of the narration's word distribution divided by narration duration, plus semantic similarity between slide text and transcript to capture cross-channel redundancy. The authors caution these are "content-derived proxy indicators" describing the presented content itself, not learners' internal cognitive states. (Shixian Zhou et al. (2026))

Claims

-

Key Sources

  • Shixian Zhou, Minghuan Shen, Xiaolin Wen, Zijun Qiu, Yongliang Jiang, Xiangyang Wu, Fei Wu, Yong Wang, and Zhiguang Zhou. (2026). SAVVY: Student Attention Visualization for Video-based Learning Analysis. arXiv. https://arxiv.org/abs/2607.29413
Page metadata
Field Value
type research-method
id savvy-content-derived-visual-and-auditory-information-density-metrics
title SAVVY content-derived visual and auditory information density metrics
description Grounded in the Limited Capacity Model of Motivated Mediated Message Processing (LC4MP), SAVVY quantifies information density of both visual and auditory channels per slide-transition-induced event segment.
status review
generated by process:settle-candidates on 2026-10-11
trust unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.