Citation: Diaz-Guerra, F.;
Jimenez-Molina, A. Continuous
Prediction of Web User Visual
Attention on Short Span Windows
Based on Gaze Data Analytics.
Sensors 2023, 23, 2294. https://
doi.org/10.3390/s23042294
Academic Editors: Antonio
Fernandez-Caballero, Guangtao Zhai
and Enrico Vezzetti
Received: 17 November 2022
Revised: 27 January 2023
Accepted: 13 February 2023
Published: 18 February 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Continuous Prediction of Web User Visual Attention on Short
Span Windows Based on Gaze Data Analytics
Francisco Diaz-Guerra
1,†,‡
and Angel Jimenez-Molina
1,2,
*
,†,§
1
Department of Industrial Engineering, University of Chile, Santiago 8370456, Chile
2
Engineering Complex Systems Institute, Santiago 8370398, Chile
* Correspondence: angeljim@uchile.cl; Tel.: +56-2-2978-0543
† These authors contributed equally to this work.
‡ Current address: Avenida Beauchef #851, Of. 514, Santiago 8370456, Chile.
§ Current address: Avenida Beauchef #851, Of. 711, Santiago 8370456, Chile.
Abstract:
Understanding users’ visual attention on websites is paramount to enhance the browsing
experience, such as providing emergent information or dynamically adapting Web interfaces. Existing
approaches to accomplish these challenges are generally based on the computation of salience maps
of static Web interfaces, while websites increasingly become more dynamic and interactive. This
paper proposes a method and provides a proof-of-concept to predict user’s visual attention on
specific regions of a website with dynamic components. This method predicts the regions of a
user’s visual attention without requiring a constant recording of the current layout of the website,
but rather by knowing the structure it presented in a past period. To address this challenge, the
concept of visit intention is introduced in this paper, defined as the probability that a user, while
browsing, will fixate their gaze on a specific region of the website in the next period. Our approach
uses the gaze patterns of a population that browsed a specific website, captured via an eye-tracker
device, to aid personalized prediction models built with individual visual kinetics features. We show
experimentally that it is possible to conduct such a prediction through multilabel classification models
using a small number of users, obtaining an average area under curve of 84.3%, and an average
accuracy of 79%. Furthermore, the user’s visual kinetics features are consistently selected in every set
of a cross-validation evaluation.
Keywords:
visual attention prediction; eye-tracker sensor; visual gaze patterns; visual kinetics;
human–computer interaction; gaze data analytics
1. Introduction
Understanding the behavior of users’ visual attention on websites is an active research
area tackled by the fields of computer vision, human–computer interaction, and Web
intelligence. By using information gleaned from this understanding, a website can be
constructed to deliver information of greater utility and complexity, such as emergent
recommendations in regions of a Web interface that capture users’ attention, adapt visual
stimuli to users’ gaze patterns in real time, among other advantages. Traditional methods
to study users’ visual attention have historically focused on images. However, recently
more complex visual stimuli have been considered, such as videos [
1
–
5
], virtual reality
environments [
6
,
7
], egocentric videos [
8
,
9
], and websites. Unfortunately, the literature
on users’ visual attention on websites is generally based on salience maps computed for
static Web interfaces [
10
–
13
], where the website structure is always known in advance [
14
].
Therefore, as dynamic and interactive websites become increasingly prevalent, traditional
methods of evaluating visual attention, such as those based on static salience maps or
pre-determined website structures, are becoming less effective.
It is imperative to gain a deeper understanding of users’ visual attention on websites
to create an optimal online experience. This requirement can be realized by dynamically
Sensors 2023, 23, 2294. https://doi.org/10.3390/s23042294 https://www.mdpi.com/journal/sensors
