The use of eye tracking in supporting individuals with dyslexia: a review

Dyslexia is a neurobiological learning disorder that significantly impairs reading fluency and accuracy. As assistive technologies evolve, eye-tracking has emerged as a critical instrument for researchers in psychology and special education. By recording eye movements—such as fixations, saccades, and regressions—researchers can gain direct, objective insights into the cognitive processes and visual-oculomotor differences that distinguish individuals with dyslexia from typical readers.

This review of 71 studies published between 2000 and 2024 highlights four primary research domains:

• Behavioral Analysis: Researchers use eye-tracking to map reading strategies and visual attention. Findings consistently show that individuals with dyslexia exhibit longer fixation durations, more frequent regressions, and less efficient binocular coordination, reflecting challenges in phonological processing and visual information retrieval.
• Material Impact: The presentation of text—including font style, size, and inter-letter spacing—significantly influences reading performance. Studies indicate that specific formatting adjustments, such as increased spacing or the use of colored overlays, can reduce cognitive load and improve reading speed for dyslexic readers.
• Detection: Machine learning has become the dominant approach for automated dyslexia screening. Models utilizing eye-tracking data, such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), have achieved high classification accuracy by analyzing raw gaze coordinates and statistical eye-movement features.
• Intervention: Eye-tracking serves as a valuable metric for assessing the effectiveness of training programs. Research shows that targeted interventions, including visual-attentional training and action video games, can lead to measurable improvements in reading accuracy and more efficient eye-movement patterns.

Understanding the specific eye-movement profiles of individuals with dyslexia allows for the development of highly personalized support strategies. By moving beyond general assessments, researchers can use eye-tracking to classify dyslexia subtypes and tailor interventions to individual needs. This review provides a roadmap for future work, emphasizing the need for larger, longitudinal studies and more diverse datasets to ensure that technological interventions are both reliable and applicable in real-world educational settings.

AI-generated third-party summary by ResearchPod. Not official content or an endorsement by the paper authors or affiliated organizations.