Exploring the similarity between game events for game level analysis and generation

Player-Game interaction can be viewed as a sequence of game events between game systems and players. In each event, a piece of information (for example, a game challenge) is presented to the player, and the player responds to that information by executing proper in-game actions. Since different games have different systems and mechanics, it is difficult to analyze and compare game events across different games. In this paper, we propose an approach to measure the similarity between game events from different games quantitatively. This similarity information can then be used to transfer probabilistic models built for analyzing and generating game levels for one game to another game.