Machine Learning algorithms to increase children motivation in cognitive training videogames

MELINA VLADISAUSKAS; LAOUEN MAYAL LOUAN BELLOLI; DIEGO FERNANDEZ SLEZAK; ANDREA P. GOLDIN

Virtual

Congreso; XXXV Reunión de la Sociedad Argentina de Investigación en Neurociencias (SAN); 2020

Sociedad Argentina de Investigación en Neurociencias

Mate Marote 1 is an open source cognitive-training software aimed at children from 5 to 8 y.o. It consists of a set of computerized games specifically tailored to train executivefunctions (EF): a class of processes critical for purposeful goal-directed behavior, including working memory, flexibility, and cognitive control. One of the current goals of theproyect is to personalize future training protocols.In our training games the complexity of a trial rapidly adjusts to the child's performance while s/he is playing. Still, all children start playing in the same, very low-challenging, level,(which could diminish the positive outcomes of the cognitive training).The goal of the present study was to develop a Machine Learning algorithm to predict a single event of the performance curve in a training game. This will allow us to know atwhich level a game becomes challenching for each child. With that information, we can preset a personalized initial difficulty level.