A Deep Learning Framework for Visual Attention Prediction and Analysis of News Interfaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kenely, Matthew, Seychell, Dylan, Debono, Carl James, Porter, Chris
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908276956856320
author Kenely, Matthew
Seychell, Dylan
Debono, Carl James
Porter, Chris
author_facet Kenely, Matthew
Seychell, Dylan
Debono, Carl James
Porter, Chris
contents News outlets' competition for attention in news interfaces has highlighted the need for demographically-aware saliency prediction models. Despite recent advancements in saliency detection applied to user interfaces (UI), existing datasets are limited in size and demographic representation. We present a deep learning framework that enhances the SaRa (Saliency Ranking) model with DeepGaze IIE, improving Salient Object Ranking (SOR) performance by 10.7%. Our framework optimizes three key components: saliency map generation, grid segment scoring, and map normalization. Through a two-fold experiment using eye-tracking (30 participants) and mouse-tracking (375 participants aged 13--70), we analyze attention patterns across demographic groups. Statistical analysis reveals significant age-based variations (p < 0.05, {ε^2} = 0.042), with older users (36--70) engaging more with textual content and younger users (13--35) interacting more with images. Mouse-tracking data closely approximates eye-tracking behavior (sAUC = 0.86) and identifies UI elements that immediately stand out, validating its use in large-scale studies. We conclude that saliency studies should prioritize gathering data from a larger, demographically representative sample and report exact demographic distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17212
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Deep Learning Framework for Visual Attention Prediction and Analysis of News Interfaces
Kenely, Matthew
Seychell, Dylan
Debono, Carl James
Porter, Chris
Computer Vision and Pattern Recognition
Human-Computer Interaction
News outlets' competition for attention in news interfaces has highlighted the need for demographically-aware saliency prediction models. Despite recent advancements in saliency detection applied to user interfaces (UI), existing datasets are limited in size and demographic representation. We present a deep learning framework that enhances the SaRa (Saliency Ranking) model with DeepGaze IIE, improving Salient Object Ranking (SOR) performance by 10.7%. Our framework optimizes three key components: saliency map generation, grid segment scoring, and map normalization. Through a two-fold experiment using eye-tracking (30 participants) and mouse-tracking (375 participants aged 13--70), we analyze attention patterns across demographic groups. Statistical analysis reveals significant age-based variations (p < 0.05, {ε^2} = 0.042), with older users (36--70) engaging more with textual content and younger users (13--35) interacting more with images. Mouse-tracking data closely approximates eye-tracking behavior (sAUC = 0.86) and identifies UI elements that immediately stand out, validating its use in large-scale studies. We conclude that saliency studies should prioritize gathering data from a larger, demographically representative sample and report exact demographic distributions.
title A Deep Learning Framework for Visual Attention Prediction and Analysis of News Interfaces
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2503.17212