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 Cross-Linguistic Coordination of Overt Attention and Speech Production as Evidence for a Language of Vision.

Cognitive science·2026
Same author

Enhancing Radiation Therapy Quality Assurance in Lymphoma: A Rigorous Real-Time Central Review Process in AHOD2131.

International journal of radiation oncology, biology, physics·2025
Same author

Leveraging Context for Perceptual Prediction Using Word Embeddings.

Cognitive science·2025
Same author

Blending into naturalistic scenes: Cortical regions serving visual search are more strongly activated in congruent contexts.

NeuroImage·2025
Same author

Uniting for Change: The GLOW Initiative and Its Impact on Nodular Lymphocyte-Predominant Hodgkin Lymphoma.

Pediatric blood & cancer·2025
Same author

The Visual Integration of Semantic and Spatial Information of Objects in Naturalistic Scenes (VISIONS) database: attentional, conceptual, and perceptual norms.

Behavior research methods·2025

Related Experiment Video

Updated: May 2, 2026

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects
07:36

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Published on: November 30, 2018

16.6K

Classification of visual and linguistic tasks using eye-movement features.

Moreno I Coco1, Frank Keller

  • 1Faculdade de Psicologia, Universidade de Lisboa, Lisboa, Portugal.

Journal of Vision
|March 11, 2014
PubMed
Summary

Classifying tasks using eye movements is possible when tasks involve different cognitive processes, like language. Eye-movement features, especially initiation time, accurately predict visual search and object naming tasks.

Keywords:
active visioncommunicative taskseye-movement featurestask classificationvisual attention

More Related Videos

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

10.3K
Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading
05:54

Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading

Published on: October 18, 2018

5.9K

Related Experiment Videos

Last Updated: May 2, 2026

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects
07:36

Eye Tracking During Visually Situated Language Comprehension: Flexibility and Limitations in Uncovering Visual Context Effects

Published on: November 30, 2018

16.6K
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

10.3K
Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading
05:54

Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading

Published on: October 18, 2018

5.9K

Area of Science:

  • Cognitive Science
  • Neuroscience
  • Computer Science

Background:

  • Task demands influence goal-directed eye movements, suggesting eye-tracking can classify tasks.
  • Previous attempts to classify visual tasks using eye-movement features have shown limited success.
  • The current study explores if incorporating tasks involving different cognitive domains, like language, improves classification accuracy.

Purpose of the Study:

  • To investigate if eye movements can accurately classify tasks that differ in cognitive domain involvement (e.g., visual search vs. language-based tasks).
  • To identify key eye-movement features that contribute to successful task classification.
  • To determine if task classification is feasible even when tasks vary in duration.

Main Methods:

  • Collected eye-movement data from participants performing three distinct tasks: visual search, object naming, and scene description.
  • Extracted previously used and novel eye-movement features, including spatial and temporal metrics.
  • Trained and evaluated three types of machine learning classifiers to predict the performed task based on extracted features.

Main Results:

  • Eye-movement responses effectively characterized the goals of the different tasks.
  • Classifiers achieved above-chance accuracy, with a maximum of 88% for visual search.
  • A single feature, initiation time, was sufficient for above-chance classification (up to 79% for object naming) and was independent of task duration.
  • Optimal classification (using seven features including spatial and temporal data) confirmed task-dependent visual attention allocation.

Conclusions:

  • Task classification using eye movements is feasible and accurate when tasks recruit different cognitive processes, extending beyond purely visual tasks.
  • Eye-movement features, particularly initiation time, provide robust indicators for classifying cognitive tasks.
  • The findings support the hypothesis that integrating tasks with varying cognitive demands enhances the efficacy of eye-tracking for task classification.