Leveraging Cluster Analysis to Understand Educational Game Player Experiences and Support Design

Luke Swanson, Field Day Lab, University of Wisconsin-Madison David Gagnon, Field Day Lab, University of Wisconsin-Madison Jennifer Scianna, Field Day Lab, University of Wisconsin-Madison John McCloskey, Field Day Lab, University of Wisconsin-Madison Nicholas Spevacek, Field Day Lab, University of Wisconsin-Madison Stefan Slater, Graduate School of Education, University of Pennsylvania Erik Harpstead, Human-Computer Interaction Institute, Carnegie Mellon University Abstract: The ability for an educational game designer to understand their audience's play styles and resulting experience is an essential tool for improving their game's design. As a game is subjected to large-scale player testing, the designers require inexpensive, automated methods for categorizing patterns of player-game interactions. In this paper we present a simple, reusable process using best practices for data clustering, feasible for use within a small educational game studio. We utilize the method to analyze a real-time strategy game, processing game telemetry data to determine categories of players based on their in-game actions, the feedback they received, and their progress through the game. Introduction Playtesting is a well-adopted method for iteratively testing and improving educational games. As a game moves through development phases, members of the target audience are given versions of the game to play, and in exchange generate feedback. This feedback can then be used to validate the design decisions made during the game's development, and to direct the next iterations of work.