A semantic generation framework for enabling adaptive game worlds

Adaptive games are expected to improve on the pre-scripted and rigid nature of traditional games. Current research uses player and experience modeling techniques to successfully predict some gameplay adjustments players desire. These are typically deployed to adapt AI behavior or to evolve content for simple game levels. In this paper we propose a generation framework aimed at creating personalized content for complex and immersive game worlds. This framework, currently under development, captures which content provided the context for a given personal gameplay experience. This model is then used to generate content for the next predicted experience, through retrieval and recombination of semantic gameplay descriptions , i.e. case-based mappings between content and player experience. Through its integration with existing player and experience modeling techniques, this framework aims at generating, in an emergent way, game worlds that better suit players. Dynamic game content, which responds to the player performance, has the ability to personalize player experience, potentially making games even more unpredictable and fun.

@InProceedings { LB11c,
  author       = "Lopes, Ricardo and Bidarra, Rafael",
  title        = "A semantic generation framework for enabling adaptive game worlds",
  booktitle    = "Proceedings of ACE 2011 - International Conference on Advances in Computer Entertainment Technology",
  month        = "nov",
  year         = "2011",
  address      = "Lisbon, Portugal",
  note         = "doi: 10.1145/2071423.2071431",
  url          = "http://graphics.tudelft.nl/Publications-new/2011/LB11c"
}