PreGLAM: A Predictive Gameplay-Based Layered Affect Model

Cale Plut, Philippe Pasquier, Jeff Ens, Renaud Bougueng

Abstract: In this article, we present the Predictive Gameplay-based Layered Affect Model (PreGLAM), an affective game spectator model that flexibly integrates into a game design process. PreGLAM combines elements of real-time player experience models and affective nonplayer-character models to output real-time estimated values for a spectator's valence, arousal, and tension during gameplay. Because tension is related to prospective events, PreGLAM attempts to predict future gameplay events. We implement and evaluate PreGLAM in a custom game Galactic Defense, which we also describe. PreGLAM significantly outperforms a random walk time series in how accurately it matches ground-truth annotations and has comparable accuracy to state-of-the-art affect models.