Discovery of Player Strategies in a Serious Game

Abstract

Serious games are popular computer games that frequently simulate real-world events or processes designed for the purpose of solving a problem. Although they are often entertaining, their main purpose is to train or educate users. Not surprisingly, users exhibit different game play behaviors because of their diverse background and game experience. To improve the educational effectiveness of these games, it is important to understand and learn from the interaction between the users and the game engine. This paper presents a study attempting to apply machine learning techniques to the game log to discover: a) strategies that are common to players interacting with serious games and b) variances in the demographics of the player base for these strategies. This is an empirical study with end-user data while playing Missing, a serious game developed to help mitigate biases that people may exhibit when analyzing plausible hypothesis for observed events. We found a set of common strategies and interesting variances in player demographics associated with these strategies.