The added value of pupillometry features to predict the experienced difficulty

Abstract

In the context of video games, dynamic difficulty adjustment (DDA) offers a dynamic solution to match the in-game difficulty to the player’s needs. In this study, we aimed to assess the added value of pupillometry features in the context of DDA and player experience modeling to predict experienced difficulty. A user study was conducted, during which participants played nine rounds of Pac-Man at different difficulties and for which gameplay-, game context- and pupillometry data were gathered together with participants’ responses regarding game experience. Multiple random forest clas- sifiers were trained on different feature subsets, with and without pupillometry features, to predict experienced difficulty. We found that the addition of pupillometry features did not lead to a performance improvement of the classifiers. This finding was supported by the results of our data analysis; only for the distributions of two of the four pupillometry features significant differences were found for the lowest and some of the other levels of self-reported experienced challenge. No convincing inverted u-curve was found to describe the relation between pupil size and experienced difficulty. A cautious inverted u-curve was found for pupil size with respect to the in-game difficulty. Based on our results we question whether pupillometry, as objective measure, is informative in the prediction of the subjective perception of difficulty. We propose future directions with respect to pupillometry features, the prediction of experienced difficulty and the prediction of the optimal load, together with a follow up study for which the constructed dataset can be reused.