Dieses Jahr feiert der Helene-Lange-Preis seine Neuauflage und Dr. Maria Rauschenberger mit Ihre Promotion “Early screening of dyslexia using a language-independent content game and machine learning” ist unter den drei Nominierten! Die Verleihung findet am 1. April im Edith-Russ-Haus für Medienkunst statt.
Der Helene-Lange-Preis richtet sich an junge (Nachwuchs-) Wissenschaftlerinnen, die sich auf besonders innovative und kreative Art und Weise mit alltagsrelevanten Aspekten der Digitalisierung befassen und die Vision haben, die Wissenschaft, Wirtschaft sowie gesellschaftliche Veränderungsprozesse in der Gegenwart und in Zukunft aktiv mitzugestalten. (15.000 Euro dotiert)
We made a huge effort and collected, clustered, and compared different applications for dyslexia for intervention, screening but also for assisted Reading or Writing. We present the result in our chapter “Technologies for Dyslexia” available in the book Web Accessibility.
Our chapter includes past, current, and future research technologies to support, intervene, or detect people with dyslexia!
The other chapters are also a great resource on Web Accessibility! If you are looking for details or a starting point for your research as well as detailed information on a specific topic like “Mathematics and Statistics”, “Multimedia Accessibility”, “Wearables”, “Mobile Web“… It is your book about recent Web Accessibility development.
With your collaboration, you would help my research immensely. The goal of our research is to contribute to the development of support tools for dyslexia in any language.
Participants play for 5-10 minutes the game DGames (see Screenshot). This game explores how children (adults) with and without dyslexia perceive musical and visual cues.
We are looking specifically for Children at the age of 7 till 12 with or without dyslexia which can easily participate in this online study. But the participants call is also open for any age. Only a computerortablet, headphones, and the Internet are needed.
The participant can speak any language as long as the parents or supervisor understands the instructions in English and can translate for the participant.
Please if you would like to participate – leave your contact details and a short description in the form and I will send you the invitation. Duration only 5 – 10 Minutes.
The data for the analysis is pseudonymized. The data will not be given to a third person. By participating in this research, you agree that Universitat Pompeu Fabra will publish the study results. This includes, for example, the results of the game or the interaction with the game. Therefore the data will be first anonymized. After that, the data will be analyzed and published. Within the possibilities, the article of the analysis for the study can be sent to you via the newsletter. Your personal information will not be published. This includes for example name or Email address.
To make a good prediction we need as many participants as possible! Participants can speak any language! Participants should be either diagnosed with dyslexia or should not show any signs of dyslexia. Please participate!
Why do I do that?
My name is Maria Rauschenberger and I was detected with dyslexia in the second grade. Since then I successfully achieved my A-Level / Highschool in 2006, graduated my Bachelor of Engineering in 2010 and graduated the Master of Science in 2015. I know how hard it is and how much effort it takes to compensate dyslexia. I know personally more people who have succeeded with dyslexia and have made a success of their lives. I want this possibility for everyone with dyslexia and therefore we need early detection. I want to create support to screen children in an easy and fun way. That’s why I am investigating possibilities with new technologies to screen children. You would really help me to achieve this goal — when you take part in my online study and play the game. Thank you.
“Kinder mit Lese-Rechtschreib-Schwäche haben auch Stärken – und die gilt es zu finden und ebenfalls zu fördern. Es ist nicht nötig, diese Kinder alleine über ihre Lese- und Rechtschreibfähigkeiten zu definieren und es gibt viele Möglichkeiten, nach der Schule Tools zu nutzen und Methoden zu entwickeln, um die Rechtschreibung zuverbessern.” – Maria Rauschenberger –
Vokabel Trainer: Learning words I frequently spell wrong with the App Semper
Spellchecker:Grammarly – still use the free version – which is helping very much to find the mistakes in English
Spellchecker:Google Docs finds lots of mistakes – good for writing anything there and then copy and past it 😉
Course for Learning how to read and write (Hamburg)
Ted Drake from Intuit and this year’s general chair of Web4All Conference 2020 is organising a series of lunch and learn session to take advantage of people working from home! The W4A keynotes of Vivienne Conway, Director (Web Key IT Pty Ltd) and Ricardo Baeza-Yates (NTENT & Khoury College of Computer Sciences Northeastern University at Silicon Valley) have been already shared. Now, they ask me to give an overview of research and technologies around dyslexia which is next Thursday on the 14th of May !
The video might be made public in any case here are the slides.
The aim of our web-game called MusVis (see Video) is to measure the reaction of children with and without dyslexia while playing, in order to find differences on their behavior. Dyslexia is a specific learning disorder that affects from 5% to 15% of the world population.
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.
Our approach aims to screen dyslexia with indicators that do not require linguistic knowledge. These indicators are probably not as strong or visible as the reading and spelling mistakes of children with dyslexia. Therefore, we consider our results (highest accuracy of 0.74 and highest F1-scores of 0.75) for German with Random Forest and (highest accuracy of 0.69) for Spanish with Extra Trees as a promising way to predict dyslexia using language-independent auditory and visual content for pre-readers.
Our approach can optimize resources for detecting and treating dyslexia, however, it would need at the beginning more personnel to screen many more children at a young age to enlarge our training data. As children with dyslexia need around two years to compensate their difficulties, our approach could help to decrease school failure, late treatment, and most importantly, to reduce suffering for children and parents.
The main advantage of our language-independent content approach is that has the potential to screen pre-readers in the near future. Indeed, we aim to collect more data with younger children to improve our results.
Maria Rauschenberger is awarded wth the fem:talent Scholarship 2017 for her research on Dyslexia.
The University of Applied Science Emden/Leer has awarded for the second time promising students and Ph.D. fellows with the fem:talent Scholarship. The students have to already succeed in their field of expertise or are expected to succeed in the future. The fem:talent Scholarship provides a financial support for a year and a pool to exchange ideas and support.
Maria Rauschenberger has received the fem:talent Scholarship twice for her research on “playful and early approach to screen children with dyslexia while playing a game”. She will be continuing her work in the next year. “I am very happy to be supported from Emden for the next phase of my Ph.D. topic. This will be hopefully very helpful for children with dyslexia in the future.”
2.April. 2018 Update: After the evaluation of the first half, also the second half of the fem:talent Scholarship (from University of Applied Science Emden/Leer) has been granted.
Do you wanna support the research on Dyslexia?
The research project is looking for children between 8 and 12 years old with dyslexia and without dyslexia. Only a computer or a tablet, headphones, and Internet are needed.
Participants can be native speakers of English, Spanish or German.
Maria’s advisors are Ricardo Baeza-Yates Professor at Universitat Pompeu Fabra & CTO of NTENT and Luz Rello Special Faculty en Cargenie Mellon University & Fundadora de Change Dyslexia. Also, special thanks to Prof. Dr. Jörg Thomaschewski from the University of Applied Science for his mentoring.