Why Reported Accuracy Can Mislead: Participant-Level Validation of Remote Facial Affect Recognition in Games, and a Player-Profiling Alternative
Reading a player’s mood from a webcam is an appealing way to build self-adjusting games: it needs no body sensors and stores only de-identified facial geometry rather than raw images. Studies in this area usually report accuracies above 80% for telling apart the difficulty-induced states we label boredom and stress. Al...