Group items tagged

Abstract: "Herein is proposed the creation of an Application Program- ming Interface (API) for the Unity 3 and 4 video game de- velopment engine that not only reads behavioral measures from traditional video game input devices (such as if there has been an increase in mouse movements and clicks) but also takes into account physiological measures from biomet- ric devices (such as an increase in respiratory rate). The API parses these inputs based on study results that correlated player performance and engagement with physio- logical signs across several dierent game genres. Through the use of several rudimentary machine learning algorithms, raw physiological data is transformed into data relevant to a developer, including player engagement. The results of these calculations allow a game designer to have powerful tools for detecting when players experience certain emotions, and al- low for the design of aective games. Furthermore, the API also exposes the raw data to de- velopers wishing to propose and utilize their own learning algorithms, to allow for a rich development environment for developers of all skill levels. These development tools will enrich the game experience for the player, as well as prepare designers for the use of the next wave of non-traditional in- put hardware. This report serves to illustrate the current status of the API. A brief overview of the signicance of galvonic skin re- sponse (GSR), heart rate (HR), and respiratory rate (RR) in detecting player performance and engagement will be fol- lowed by a discussion of the API itself and the design choices therein."

Abstract: "In this paper, we describe a methodology for capturing player experience while interacting with a game and we present a data-driven approach for modeling this interaction. We believe the best way to adapt games to a specic player is to use quantitative models of player ex- perience derived from the in-game interaction. Therefore, we rely on crowd-sourced data collected about game context, players behavior and players self-reports of dierent aective states. Based on this informa- tion, we construct estimators of player experience using neuroevolution- ary preference learning. We present the experimental setup and the re- sults obtained from a recent case study where accurate estimators were constructed based on information collected from players playing a rst- person shooter game. The framework presented is part of a bigger picture where the generated models are utilized to tailor content generation to particular player's needs and playing characteristics."