Measurement and verification of cognitive load in multimedia presentation using an eye tracker

The development of interface designs can reduce extraneous processing for users and increase the effectiveness of multimedia presentations. In this study, we investigate cognitive load in multimedia presentations. First, we present a quantitative model to measure cognitive load in terms of information comprehension in which the pupil diameter variation is used as an indicator of cognitive load based on cognitive load theory. We design a verification experiment to measure the pupil diameter using an eye-tracker when different combinations of texts, audio-narrations, and images are presented to subjects. We further allow the subjects take a comprehension test on the presented information and analyze the relationship between cognitive load and the test score using the generalized linear mixed model (GLMM). Moreover, we obtain the subjective cognitive load via a pre-designed questionnaire taken after the experiment and compare these two types of cognitive loads in terms of the mean absolute error (MAE). The experiment results show that there is a gap between the objective cognitive load obtained via the pupillary response and the subjective cognitive load obtained via a questionnaire, and the presentation with an optimized combination of multimedia can enhance information comprehension while reducing cognitive load.