Linguistic Comparison of Children with and without ASD through Eye-Tracking Data

Abstract

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder that affects a child's social communication development, and early assessment is a challenging and time-consuming practice. Over the years, research has shown that eye-tracking (ET) data provides valuable information for clinical practice. Many data analytics methods have been developed to assess ASD in young children. Although mainly predictive techniques are used in the literature, it has also been shown that using descriptive techniques can lead to a common understanding in this specific area. Well-known statistical analyses are insufficient to provide explicit knowledge compatible with human understanding. Therefore, linguistic summarization techniques are helpful in meeting this need. The dataset provided by the ETJASD Project has been utilized in this study to create human-friendly fuzzy linguistic summaries. To the best of our knowledge, it is one of the first studies that linguistically summarize eye tracking data. The outcomes are presented in a comparative manner between children with and without ASD.