During the last ten years, games have become big business, generating higher revenues than Hollywood. Games evolved from single player games to massive multiplayer platforms with hundreds or even millions of players simultaneously that often include complex world simulations. On the one hand this requires more and more sophisticated methods for automation where fraud detection, story generation, adapting game AI or matchmaking are only a few of the novel challenges that have to be targeted by the industry. On the other hand, with the introduction of games on social networking sites came the birth of a new type of game-related data source that presents a new and possibly high pay-off application for data mining research.
We welcome submissions on all aspects of Machine Learning and Data Mining for and in games, including, but not limited to, papers addressing the following topics:
- Learning how to play games well for games ranging from deterministic and discrete board games to non-deterministic, continuous, real time, action oriented games.
- Player/opponent/team modeling and game analysis for goals such as improving artificial players in competitive games, mimicking human players, game or learning curve adaptation, automatic skill-ranking, match-making, or player and team behavior analysis (fraud detection) in multiplayer games.
- Game adaptivity and automated content or story generation, for example for raising or lowering difficulty levels dependent on the players proficiency and avoiding the emergence of player routines that are guaranteed to beat the game, possibly with attention to user specific constraints and preferences. This topic also includes concerns on game stability and performance guarantees for artificial opponents and issues related to the learning experience and the design of virtual humans in serious games.
- Novel data mining challenges and/or techniques for data generated through computer games, for example using logs from social, massively multi-player or mobile games to gain insight on human behaviour or understand social and group dynamics amongst players, or learning when and why players will quit a game out of frustration.
- Data mining and machine learning perspectives in/from the games industry.
We also welcome on topic work-in-progress contributions, position papers, as well as papers discussing potential research directions. Submissions will be reviewed by program committee members on the basis of relevance, significance, technical quality, and clarity. All accepted papers will be presented as posters and among them, a few will be selected for oral presentation.
- Tom Croonenborghs, Katholieke Hogeschool Kempen
- Kurt Driessens, Maastricht University
- Olana Missura, Fraunhofer IAIS and University of Bonn