Detecting dyslexia with interactions that do not require a knowledge of language

Summary: A new web-based game that is independent of language can help to detect dyslexia in children.

Source: UPF Barcelona

Dyslexia is a specific learning disorder that affects 5 – 15% of the world population. MusVis, a web game developed by Maria Rauschenberger supervised by Ricardo Baeza-Yates and Luz Rello, researchers associated with the Department of Information and Communication Technologies (DTIC) at UPF, received the W4A Attendees’ Award on 20 April at the 17th International Web for All Conference, whose specific theme this year was Automation for Accessibility, for the communication paper entitled “Screening risk of dyslexia through a web-game using language-independent content and machine learning”.

“The aim of our web game, called MusVis, was to measure the differences in the interaction of children with and without dyslexia while they identify visual and musical elements in a fun way”, says Maria Rauschenberger, a 2019 PhD from Pompeu Fabra University with her thesis on dyslexia supervised by Ricardo Baeza-Yates and Luz Rello, co-authors of the paper and researchers associated with the UPF DTIC. Thanks to her research, Maria Rauschenberger was hired as a postdoctoral researcher at the Max-Planck Research Institute in Germany.

“To our knowledge, this is the first time the risk of dyslexia has been analysed by means of a web game based on language-independent contents and using machine learning”, Rauschenberger affirms. This new method could be used to detect possible learning disorders in children, even before they develop language skills, and lead to possible early intervention. Thus, “we aimed to detect dyslexia through interactions that do not require a knowledge of language”, the authors affirm.

This shows test symbols
The first row shows the correct symbol and the following the distractors for the four different stages of the visual part of the game. Image is credited to UPF.

Although it is likely that the differences are not as strong or visible as reading and spelling errors that characterize children with dyslexia, in the light of the results obtained so far, the authors consider MusVis as being a promising tool for predicting dyslexia in pre-readers using language-independent audio and visual content. “Since children with dyslexia need about two years to offset their difficulties, our method, as it is language-independent, could help reduce school failure, delayed treatment and, most importantly, reduce the suffering of children and parents”, Rauschenberg highlights.

“Our approach might optimize the resources to detect and treat dyslexia, however, we would need to examine many more children at an early age to expand the training data for our predictive models based on machine learning and improve our results”, the authors add.

Hence, all children who so wish are invited to participate in this study from home, via this page:

About this neuroscience research article

UPF Barcelona
Media Contacts:
Nuria Pérez – UPF Barcelona
Image Source:
The image is credited to UPF.

Original Research: Open access
“Screening risk of dyslexia through a web-game using language-independent content and machine learning”. by
Maria Rauschenberger, Ricardo Baeza-Yates, Luz Rello.
Proceedings of the 17th International Web for All Conference doi:10.1145/3371300.3383342


Screening risk of dyslexia through a web-game using language-independent content and machine learning

Children with dyslexia are often diagnosed after they fail school even if dyslexia is not related to general intelligence. In this work, we present an approach for universal screening of dyslexia using machine learning models with data gathered from a web-based language-independent game. We designed the game content taking into consideration the analysis of mistakes of people with dyslexia in different languages and other parameters related to dyslexia like auditory perception as well as visual perception. We did a user study with 313 children (116 with dyslexia) and train predictive machine learning models with the collected data. Our method yields an accuracy of 0.74 for German and 0.69 for Spanish as well as a F1-score of 0.75 for German and 0.75 for Spanish, using Random Forests and Extra Trees, respectively. To the best of our knowledge this is the first time that risk of dyslexia is screened using a language-independent content web-based game and machine-learning. Universal screening with language-independent content can be used for the screening of pre-readers who do not have any language skills, facilitating a potential early intervention.

Feel Free To Share This Neuroscience News.

Join our Newsletter
I agree to have my personal information transferred to AWeber for Neuroscience Newsletter ( more information )
Sign up to receive our recent neuroscience headlines and summaries sent to your email once a day, totally free.
We hate spam and only use your email to contact you about newsletters. You can cancel your subscription any time.