Eye-Tracking Data for Cognitive Style Classification from 85 Participants

Data Sheet 1_Machine learning-driven model construction for automated classification of cognitive styles.pdf is a research dataset by Xiangwen Wu, last updated in April 2026. It contains eye-movement data from 85 participants, used to develop a machine learning model for classifying verbal versus representational cognitive styles. The study extracted multidimensional eye-movement features and evaluated six algorithms, with SVM achieving 82.1% classification accuracy.

Use Cases

• Training machine learning models for cognitive style classification based on objective eye-movement features.
• Benchmarking algorithm performance (e.g., SVM, decision tree, logistic regression) on physiological data.
• Developing real-time adaptive learning systems based on inferred cognitive styles.
• Informing the design of personalized learning interfaces and cognitive-perceptual computing systems.

Strengths

• Includes data from 85 participants, providing a basis for model development.
• Model performance is quantified, with SVM achieving 82.1% classification accuracy.
• Uses objective physiological data (eye-tracking) to mitigate subjectivity bias from self-reports.

Limitations

• Row count and column-level documentation are unknown, limiting suitability assessment.
• The dataset is small (130.7 KB), indicating limited scope and sample size.
• Data may reflect bias inherent to the specific experimental setup and participant pool.

Provenance

Source

Xiangwen Wu via figshare.

Collection Method

Eye-movement data collected via eye-tracking technology during a standardized cognitive task.

Time Range

null

Freshness

Last updated 2026-04-09 12:12:10.

Geography

null