Screening dyslexia for English using HCI measures and machine learning
| Autor: | Luz Rello, Jeffrey P. Bigham, Nancy Cushen White, Maria Rauschenberger, Enrique Romero, Kristin Williams, Abdullah Ali |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Serious games
Informàtica::Intel·ligència artificial::Aprenentatge automàtic [Àrees temàtiques de la UPC] media_common.quotation_subject Population Early detection 02 engineering and technology Machine learning computer.software_genre Dyslexia Perception Diagnosis Aprenentatge automàtic 0202 electrical engineering electronic engineering information engineering medicine 0501 psychology and cognitive sciences Cognitive skill education 050107 human factors media_common education.field_of_study Working memory business.industry 05 social sciences Dislèxia 020207 software engineering Statistical model Linguistics medicine.disease Executive functions Screening ComputingMilieux_COMPUTERSANDSOCIETY Artificial intelligence Psychology business computer |
| Zdroj: | DH Recercat. Dipósit de la Recerca de Catalunya instname UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) |
| Popis: | More than 10% of the population has dyslexia, and most are diagnosed only after they fail in school. This work seeks to change this through early detection via machine learning models that predict dyslexia by observing how people interact with a linguistic computer-based game. We designed items of the game taking into account (i) the empirical linguistic analysis of the errors that people with dyslexia make, and (ii) specific cognitive skills related to dyslexia: Language Skills, Working Memory, Executive Functions, and Perceptual Processes. . Using measures derived from the game, we conducted an experiment with 267 children and adults in order to train a statistical model that predicts readers with and without dyslexia using measures derived from the game. The model was trained and evaluated in a 10-fold cross experiment, reaching 84.62% accuracy using the most informative features. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|