Reading failure of children is a systemic problem across the United States (U.S.). Over 60% of U.S. children never achieve reading proficiency during their K-12 education. An even greater gap exists for children with disabilities who are at risk for persistent struggles with reading or a Reading Disability (RD). Researchers have shown when reading failure goes unaddressed negative effects persist for children into adulthood in various aspects of life. Early reading interventions show promise in remedying RD; however, traditional measures for identifying children with RD are costly, time-consuming, and unreliable. Researchers have revealed that Artificial Intelligence (AI) tools, such as eye-tracking, can potentially detect RD for earlier intervention. Currently, limited research exists on eye-tracking to identify elementary children potentially at risk for RD. The purpose of this study was to investigate the potential impact of using eye-tracking during a reading screening to determine if significant differences existed between the (a) average fixation time and (b) proportions of fixations to total stimuli duration while reading with 12 children with RD and 17 children without RD. A study powered at 80% showed, statistically significant differences for children with RD having longer average fixation times compared to children without RD. The researcher found a statistically significant similarity between groups with a low average of proportions of fixations to total stimuli duration while reading between children without an RD. The findings from this exploratory study indicate potential for further use and investigation of employing eye-tracking devices combined with AI to screen, identify, and progress monitor elementary children potentially at risk for or identified with RD.
| Identifer | oai:union.ndltd.org:ucf.edu/oai:stars.library.ucf.edu:etd2020-2856 |
| Date | 15 August 2023 |
| Creators | Berns-Conner, Monica |
| Publisher | STARS |
| Source Sets | University of Central Florida |
| Language | English |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Electronic Theses and Dissertations, 2020- |
Page generated in 0.0022 seconds