Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The Use of Osteo-Inductive 3D-Printed Scaffolds Covered with a Pleiotrophin Peptide for Bone Defects: An In Vivo Experimental Study.

Bioengineering (Basel, Switzerland)·2026
Same author

Associations Between Hip Mobility and Pain in Chronic Low Back Pain Using IMU and Markerless Motion Capture.

Sensors (Basel, Switzerland)·2026
Same author

Investigating the feasibility and acceptability of the TeleRehabilitation of balance clinical and economic Decision Support System (TeleRehaB DSS) in adults at risk of falls: study protocol for a multicentre clinical trial.

BMJ open·2026
Same author

Efficacy of the Shear Stress Pattern Computed in Coronary Artery Reconstruction Models With and Without Side Branches in Predicting Plaque Progression.

Arteriosclerosis, thrombosis, and vascular biology·2026
Same author

Distinguishing Gait Patterns in PD Patients Under Different Treatments via Recurrence Plots and Vision Transformer Fusion.

IEEE open journal of engineering in medicine and biology·2026
Same author

Key factors in developing effective digital health promotion tools for cancer prevention and health behavior change in adolescence through a multi-country survey.

BMC public health·2026

Related Experiment Video

Updated: Jul 30, 2025

Loneliness Assuaged: Eye-Tracking an Audience Watching Barrage Videos
06:45

Loneliness Assuaged: Eye-Tracking an Audience Watching Barrage Videos

Published on: May 29, 2020

4.2K

eSEE-d: Emotional State Estimation Based on Eye-Tracking Dataset.

Vasileios Skaramagkas1,2, Emmanouil Ktistakis1,3, Dimitris Manousos1

  • 1Institute of Computer Science, Foundation for Research and Technology Hellas (FORTH), GR-700 13 Heraklion, Greece.

Brain Sciences
|May 16, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces the eSEE-d database for emotional state estimation using eye-tracking data. Promising results show high accuracy in classifying emotional valence and arousal using eye and gaze features.

Keywords:
affective computingarousalemotion classificationemotion databaseeye trackingneural networksvalence

More Related Videos

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
07:48

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

439
Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes
10:43

Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes

Published on: June 10, 2021

5.4K

Related Experiment Videos

Last Updated: Jul 30, 2025

Loneliness Assuaged: Eye-Tracking an Audience Watching Barrage Videos
06:45

Loneliness Assuaged: Eye-Tracking an Audience Watching Barrage Videos

Published on: May 29, 2020

4.2K
Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
07:48

Eye Tracking During A Complex Aviation Task For Insights Into Information Processing

Published on: April 4, 2025

439
Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes
10:43

Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes

Published on: June 10, 2021

5.4K

Area of Science:

  • Psychology
  • Computer Science
  • Human-Computer Interaction

Background:

  • Affective state estimation is a growing research area driven by AI advancements and video availability.
  • Limited public datasets hinder the development and comparison of new methodologies in emotion recognition.
  • Eye-tracking data offers a promising, objective modality for understanding emotional responses.

Purpose of the Study:

  • To introduce the eSEE-d database, a novel resource for emotional state estimation using eye-tracking data.
  • To analyze correlations between eye/gaze features and self-reported emotional states (arousal, valence).
  • To develop and evaluate a deep learning model for classifying emotional states based solely on eye-tracking metrics.

Main Methods:

  • Recorded eye movements of 48 participants watching emotion-evoking and neutral videos.
  • Collected participant ratings of emotions, arousal, and valence, alongside self-assessment questionnaires.
  • Extracted eye and gaze features from recorded data and applied a Deep Multilayer Perceptron (DMLP) network for classification.

Main Results:

  • Investigated correlations between extracted eye/gaze features and participants' emotional ratings.
  • Achieved 92% accuracy in distinguishing positive valence from non-positive states using the DMLP model.
  • Demonstrated 81% accuracy in differentiating low arousal from medium arousal states.

Conclusions:

  • The eSEE-d database provides a valuable resource for advancing affective state estimation research.
  • Eye and gaze features are effective predictors of emotional arousal and valence.
  • The developed DMLP model shows significant potential for objective emotion recognition using eye-tracking data.