Real-time rule-based classification of player types in computer games

Ben Cowley, DK Charles, Michaela Black, RJ Hickey

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

The power of using machine learning to improve or investigate the experience of play is only beginning to be realised. For instance, the experience of play is a psychological phenomenon, yet common psychological concepts such as the typology of temperaments have not been widely utilised in game design or research. An effective player typology provides a model by which we can analyse player behaviour. We present a real-time classifier of player type, implemented in the test-bed game Pac-Man. Decision Tree algorithms CART and C5.0 were trained on labels from the DGD player typology (Bateman and Boon, 21st century game design, vol. 1, 2005). The classifier is then built by selecting rules from the Decision Trees using a rule- performance metric, and experimentally validated. We achieve ~70% accuracy in this validation testing. We further analyse the concept descriptions learned by the Decision Trees. The algorithm output is examined with respect to a set of hypotheses on player behaviour. A set of open questions is then posed against the test data obtained from validation testing, to illustrate the further insights possible from extended analysis.
LanguageEnglish
Pages489-526
JournalUser Modeling and User-Adapted Interaction
Volume23
Issue number5
DOIs
Publication statusPublished - Nov 2013

Fingerprint

Computer games
computer game
Decision trees
typology
Classifiers
Testing
Learning systems
Labels
experience
learning
performance
time

Cite this

@article{218eb01386d549df8bd31686bb3fdde8,
title = "Real-time rule-based classification of player types in computer games",
abstract = "The power of using machine learning to improve or investigate the experience of play is only beginning to be realised. For instance, the experience of play is a psychological phenomenon, yet common psychological concepts such as the typology of temperaments have not been widely utilised in game design or research. An effective player typology provides a model by which we can analyse player behaviour. We present a real-time classifier of player type, implemented in the test-bed game Pac-Man. Decision Tree algorithms CART and C5.0 were trained on labels from the DGD player typology (Bateman and Boon, 21st century game design, vol. 1, 2005). The classifier is then built by selecting rules from the Decision Trees using a rule- performance metric, and experimentally validated. We achieve ~70{\%} accuracy in this validation testing. We further analyse the concept descriptions learned by the Decision Trees. The algorithm output is examined with respect to a set of hypotheses on player behaviour. A set of open questions is then posed against the test data obtained from validation testing, to illustrate the further insights possible from extended analysis.",
author = "Ben Cowley and DK Charles and Michaela Black and RJ Hickey",
year = "2013",
month = "11",
doi = "10.1007/s11257-012-9126-z",
language = "English",
volume = "23",
pages = "489--526",
journal = "User Modeling and User-Adapted Interaction",
issn = "0924-1868",
number = "5",

}

Real-time rule-based classification of player types in computer games. / Cowley, Ben; Charles, DK; Black, Michaela; Hickey, RJ.

In: User Modeling and User-Adapted Interaction, Vol. 23, No. 5, 11.2013, p. 489-526.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-time rule-based classification of player types in computer games

AU - Cowley, Ben

AU - Charles, DK

AU - Black, Michaela

AU - Hickey, RJ

PY - 2013/11

Y1 - 2013/11

N2 - The power of using machine learning to improve or investigate the experience of play is only beginning to be realised. For instance, the experience of play is a psychological phenomenon, yet common psychological concepts such as the typology of temperaments have not been widely utilised in game design or research. An effective player typology provides a model by which we can analyse player behaviour. We present a real-time classifier of player type, implemented in the test-bed game Pac-Man. Decision Tree algorithms CART and C5.0 were trained on labels from the DGD player typology (Bateman and Boon, 21st century game design, vol. 1, 2005). The classifier is then built by selecting rules from the Decision Trees using a rule- performance metric, and experimentally validated. We achieve ~70% accuracy in this validation testing. We further analyse the concept descriptions learned by the Decision Trees. The algorithm output is examined with respect to a set of hypotheses on player behaviour. A set of open questions is then posed against the test data obtained from validation testing, to illustrate the further insights possible from extended analysis.

AB - The power of using machine learning to improve or investigate the experience of play is only beginning to be realised. For instance, the experience of play is a psychological phenomenon, yet common psychological concepts such as the typology of temperaments have not been widely utilised in game design or research. An effective player typology provides a model by which we can analyse player behaviour. We present a real-time classifier of player type, implemented in the test-bed game Pac-Man. Decision Tree algorithms CART and C5.0 were trained on labels from the DGD player typology (Bateman and Boon, 21st century game design, vol. 1, 2005). The classifier is then built by selecting rules from the Decision Trees using a rule- performance metric, and experimentally validated. We achieve ~70% accuracy in this validation testing. We further analyse the concept descriptions learned by the Decision Trees. The algorithm output is examined with respect to a set of hypotheses on player behaviour. A set of open questions is then posed against the test data obtained from validation testing, to illustrate the further insights possible from extended analysis.

U2 - 10.1007/s11257-012-9126-z

DO - 10.1007/s11257-012-9126-z

M3 - Article

VL - 23

SP - 489

EP - 526

JO - User Modeling and User-Adapted Interaction

T2 - User Modeling and User-Adapted Interaction

JF - User Modeling and User-Adapted Interaction

SN - 0924-1868

IS - 5

ER -