LudoScience

Informations

Support : Références scientifiques
Auteur(s) : Ramla Ghali, Sébastien Ouellet, Claude Frasson
Editeur : KI 2015: the 38th German Conference on Artificial intelligence, short paper, Dresden, Germany, September 21-25, 2015
Date : 2015
Langue :

Description

In this paper, we will present an educational game that we developed

in order to teach a chemistry lesson, namely drawing a Lewis diagram. We also

conducted an experiment to gather data about the cognitive and emotional

states of the learners as well as their behaviour through out our game

by using three types of sensors (electroencephalography,eye tracking, and facial

expression recognition with an optical camera)

.

Primary results show that a machine learning model (logistic regression)

can predict with some success whet her the learner will give a correct or a wrong

answer to a task presented in the game, and paves the way for an adaptive version

of the game. This latter will challenge or assist learners based on some features

extracted from our data in order to provide real-time adaptation specific to the user

 

Références (1) :

 

Alvarez, J. and L. Michaud (2008). Serious Games: Advergaming, edugaming, training and more IDATE 

Mots-clés : Educational game, Electroencephalogram, Eyetracking, Facial ex-pression recognition, Logistic regression model

---

---