| Popis: |
Worldwide, approximately 10% of the population suffers from dyslexia. Specific learning disabilities. Most previouseye tracking with people with and without dyslexia have found that differences between populations, suggesting thateye movement that eye movements reflect the difficulties of people with dyslexia. On the website we present the firststatistical model that can predict dyslexic and non-dyslexic readers using eye tracking measures. Eye tracking. Themodel is trained and evaluated in a ten-fold cross-validation test. Experiment with a dataset consisting of 1,135 readings.individuals with and without dyslexia that were recorded using eye tracker. Our model, based on Support Vector Machine binary classifier, achieves 80.18% accuracy using the most informative features. To the best of our knowledge, thisis the first time eye tracking measures are used to automatic prediction of dyslexic readers using machine learning. |
