Predicting Player Experience without the Player

Christian Guckelsberger; Christian Salge; Jeremy Gow; Paul Antony Cairns

Predicting Player Experience without the Player

Christian Guckelsberger, Christian Salge, Jeremy Gow, Paul Antony Cairns

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English
Title of host publication	ACM CHI Play 2017
Publisher	ACM
Pages	305-315
Publication status	Published - Oct 2017

Cite this

@inproceedings{c6c61aa8d80f4dfebdb253ae64531f97,

title = "Predicting Player Experience without the Player",

abstract = "A key challenge of procedural content generation (PCG) isto evoke a certain player experience (PX), when we have nodirect control over the content which gives rise to that experience.We argue that neither the rigorous methods to assess PXin HCI, nor specialised methods in PCG are sufficient, becausethey rely on a human in the loop. We propose to address thisshortcoming by means of computational models of intrinsicmotivation and AI game-playing agents. We hypothesise thatour approach could be used to automatically predict PX acrossgames and content types without relying on a human player ordesigner. We conduct an exploratory study in level generationbased on empowerment, a specific model of intrinsic motivation.Based on a thematic analysis, we find that empowermentcan be used to create levels with qualitatively different PX. Werelate the identified experiences to established theories of PXin HCI and game design, and discuss next steps.",

author = "Christian Guckelsberger and Christian Salge and Jeremy Gow and Cairns, {Paul Antony}",

year = "2017",

month = oct,

language = "English",

pages = "305--315",

booktitle = "ACM CHI Play 2017",

publisher = "ACM",

address = "United States",

}

TY - GEN

T1 - Predicting Player Experience without the Player

AU - Guckelsberger, Christian

AU - Salge, Christian

AU - Gow, Jeremy

AU - Cairns, Paul Antony

PY - 2017/10

Y1 - 2017/10

N2 - A key challenge of procedural content generation (PCG) isto evoke a certain player experience (PX), when we have nodirect control over the content which gives rise to that experience.We argue that neither the rigorous methods to assess PXin HCI, nor specialised methods in PCG are sufficient, becausethey rely on a human in the loop. We propose to address thisshortcoming by means of computational models of intrinsicmotivation and AI game-playing agents. We hypothesise thatour approach could be used to automatically predict PX acrossgames and content types without relying on a human player ordesigner. We conduct an exploratory study in level generationbased on empowerment, a specific model of intrinsic motivation.Based on a thematic analysis, we find that empowermentcan be used to create levels with qualitatively different PX. Werelate the identified experiences to established theories of PXin HCI and game design, and discuss next steps.

AB - A key challenge of procedural content generation (PCG) isto evoke a certain player experience (PX), when we have nodirect control over the content which gives rise to that experience.We argue that neither the rigorous methods to assess PXin HCI, nor specialised methods in PCG are sufficient, becausethey rely on a human in the loop. We propose to address thisshortcoming by means of computational models of intrinsicmotivation and AI game-playing agents. We hypothesise thatour approach could be used to automatically predict PX acrossgames and content types without relying on a human player ordesigner. We conduct an exploratory study in level generationbased on empowerment, a specific model of intrinsic motivation.Based on a thematic analysis, we find that empowermentcan be used to create levels with qualitatively different PX. Werelate the identified experiences to established theories of PXin HCI and game design, and discuss next steps.

M3 - Conference contribution

SP - 305

EP - 315

BT - ACM CHI Play 2017

PB - ACM

ER -