Currently submitted to: JMIR Serious Games
Date Submitted: Jun 19, 2020
Open Peer Review Period: Jun 19, 2020 - Aug 14, 2020
(currently open for review)
Game and Pupillometry Data for Cognitive Load Measurement: Classifying Cognitive Load of Educational Video Game Levels
Besides the current challenge, the perceived difficulty level of a learning task depends on the student's previous knowledge and skills. When a learning task is recurrently perceived as easy (or hard), it may cause poor learning results. Gamer data such as errors, attempts, or time to finish a challenge are widely used to estimate the perceived difficulty level. In other contexts, pupillometry is widely used to measure the cognitive load (mental effort); hence, this may describe the perceived task difficulty.
This study aimed to assess the use of pupillary data as a cognitive load measure for describing the difficulty levels in a video game. Also, it proposes an image filter to better estimate the baseline pupil size and to reduce the screen luminescence effect.
We conducted an experiment that compares the baseline estimated from our filter against that estimated from common approaches. Different pupil features were used to classify the difficulty of a dataset containing information from students playing a video game for practicing math fractions.
Results showed that the proposed filter allows to better estimate a baseline, Mauchly’s Test of Sphericity indicated that the assumption of sphericity had been violated, χ2(14) =0.045389, p = .001; and therefore, a Greenhouse-Geisser correction was used, ε = 0.47, there was a significant difference against Mean Pupil Diameter Change (MPDC) estimated from different baseline images with the scramble filter, F(2.35) = 30.965, p < .001. Moreover, according to the Wilcoxon signed-rank test, pupillary features that better describe the difficulty level were MPDC (Z = -2.15, p <0.05) and Peak Dilation (Z = -3.58, p<0.00); a random forest classifier for easy- and hard-level of difficult showed an accuracy of 75% when the gamer data is used, but the accuracy increases to 87.5 % by including pupillary measurements.
The screen luminescent effect on pupil size was reduced with a scrambled filter on the background video game image. Finally, pupillary data can improve the classifier accuracy of the perceived difficulty of gamers in educational video games.
Request queued. Please wait while the file is being generated. It may take some time.
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.