Considering the detrimental effects of dyslexia on academic performance and its common occurrence, developing tools for dyslexia detection, monitoring, and treatment poses a task of significant priority. The research performed in this paper was focused on detecting and analyzing dyslexic tendencies in Serbian children based on eye-tracking measures. The group of 30 children (ages 7–13, 15 dyslexic and 15 non-dyslexic) read 13 different text segments on 13 different color configurations. For each text segment, the corresponding eye-tracking trail was recorded and then processed offline and represented by nine conventional features and five newly proposed features. The features were used for dyslexia recognition using several machine learning algorithms: logistic regression, support vector machine, k-nearest neighbor, and random forest. The highest accuracy of 94% was achieved using all the implemented features and leave-one-out subject cross-validation. Afterwards, the most important features for dyslexia detection (representing the complexity of fixation gaze) were used in a statistical analysis of the individual color effects on dyslexic tendencies within the dyslexic group. The statistical analysis has shown that the influence of color has high inter-subject variability. This paper is the first to introduce features that provide clear separability between a dyslexic and control group in the Serbian language (a language with a shallow orthographic system). Furthermore, the proposed features could be used for diagnosing and tracking dyslexia as biomarkers for objective quantification.

No abstract

The negative influence of developmental dyslexia on academic performance is a welldocumented and researched topic. Although research focused on developmental dyslexia detection and evaluation is plentiful, the study designs vary to a great degree, making the exchange of obtained knowledge often difficult. This paper focuses on bridging the gap between different study designs by developing a machine learning based pipeline that was evaluated on two completely different eye-tracking datasets (training on one, testing on the other, and vice versa). One dataset included 30 subjects who read text written in Serbian on different color configurations and were tracked with a remote eye-tracker. The second dataset included 185 subjects who read text written in Swedish, and recorded eye-tracking data using a goggle-based system. The data from both datasets was converted to grayscale images, using various time window configurations to parse the signals, and plotting the data in a 2D plane. The train images were used to train an Autoencoder neural network, and the images' reconstruction error was used to create features that describe each instance of both the training and test sets. The train feature set was used to train various machine learning algorithms, which were then evaluated on the testing feature dataset. A classification accuracy of 85.6% was obtained when testing on Serbian readers' data and 82.9% when testing on Swedish readers. The proposed pipeline was shown to be transferable between the datasets, despite many differences in the experiment design, showing potential in combining various eye-tracking dyslexia studies.

Developing reliable, quantifiable, and accessible metrics for dyslexia diagnosis and tracking represents an important goal, considering the widespread nature of dyslexia and its negative impact on education and quality of life. In this study, we observe eye-tracking data from 15 dyslexic and 15 neurotypical Serbian school-age children who read text segments presented on different color configurations. Two new eye-tracking features were introduced that quantify the amount of spatial complexity of the subject’s gaze through time and inherently provide information regarding the locations in the text in which the subject struggled the most. The features were extracted from the raw eye-tracking data (x, y coordinates), from the original data gathered at 60 Hz, and from the downsampled data at 30 Hz, examining the compatibility of features with low-cost or custom-made eye-trackers. The features were used as inputs to machine learning algorithms, and the best-obtained accuracy was 88.9% for 60 Hz and 87.8% for 30 Hz. The features were also used to analyze the influence of background/overlay color on the quality of reading, and it was shown that the introduced features separate the dyslexic and control groups regardless of the background/overlay color. The colors can, however, influence each subject differently, which implies that an individualistic approach would be necessary to obtain the best therapeutic results. The performed study shows promise in dyslexia detection and evaluation, as the proposed features can be implemented in real time as feedback during reading and show effectiveness at detecting dyslexia with data obtained using a lower sampling rate.