Predicting Player Experience without the Player.: An Exploratory Study. Guckelsberger, C., Salge, C., Gow, J., & Cairns, P. In Proceedings of the Annual Symposium on Computer-Human Interaction in Play, of CHI PLAY '17, pages 305–315, New York, NY, USA, 2017. Association for Computing Machinery. 19 citations (Crossref) [2023-05-15] event-place: Amsterdam, The Netherlands
Predicting Player Experience without the Player.: An Exploratory Study [link]Paper  doi  abstract   bibtex   
A key challenge of procedural content generation (PCG) is to evoke a certain player experience (PX), when we have no direct control over the content which gives rise to that experience. We argue that neither the rigorous methods to assess PX in HCI, nor specialised methods in PCG are sufficient, because they rely on a human in the loop. We propose to address this shortcoming by means of computational models of intrinsic motivation and AI game-playing agents. We hypothesise that our approach could be used to automatically predict PX across games and content types without relying on a human player or designer. We conduct an exploratory study in level generation based on empowerment, a specific model of intrinsic motivation. Based on a thematic analysis, we find that empowerment can be used to create levels with qualitatively different PX. We relate the identified experiences to established theories of PX in HCI and game design, and discuss next steps.
@inproceedings{guckelsberger_predicting_2017,
	address = {New York, NY, USA},
	series = {{CHI} {PLAY} '17},
	title = {Predicting {Player} {Experience} without the {Player}.: {An} {Exploratory} {Study}},
	isbn = {978-1-4503-4898-0},
	url = {https://doi.org/10.1145/3116595.3116631},
	doi = {10.1145/3116595.3116631},
	abstract = {A key challenge of procedural content generation (PCG) is to evoke a certain player experience (PX), when we have no direct control over the content which gives rise to that experience. We argue that neither the rigorous methods to assess PX in HCI, nor specialised methods in PCG are sufficient, because they rely on a human in the loop. We propose to address this shortcoming by means of computational models of intrinsic motivation and AI game-playing agents. We hypothesise that our approach could be used to automatically predict PX across games and content types without relying on a human player or designer. We conduct an exploratory study in level generation based on empowerment, a specific model of intrinsic motivation. Based on a thematic analysis, we find that empowerment can be used to create levels with qualitatively different PX. We relate the identified experiences to established theories of PX in HCI and game design, and discuss next steps.},
	booktitle = {Proceedings of the {Annual} {Symposium} on {Computer}-{Human} {Interaction} in {Play}},
	publisher = {Association for Computing Machinery},
	author = {Guckelsberger, Christian and Salge, Christoph and Gow, Jeremy and Cairns, Paul},
	year = {2017},
	note = {19 citations (Crossref) [2023-05-15]
event-place: Amsterdam, The Netherlands},
	keywords = {AI players, empowerment, models of intrinsic motivation, player experience, procedural content generation},
	pages = {305--315},
}

Downloads: 0