Like a DNA string: Sequence-based Player Profiling in Tom Clancy’s The Division

Sasha  Makarovych; Alessandro Canossa; Julian Togelius; Anders Drachen

Like a DNA string: Sequence-based Player Profiling in Tom Clancy’s The Division

Sasha Makarovych, Alessandro Canossa, Julian Togelius, Anders Drachen

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

In this paper we present an approach for using sequence analysis
to model player behavior. This approach is designed
to work in game development contexts, integrating production
teams and delivering profiles that inform game design.
We demonstrate the method via a case study of the game
Tom Clancy’s The Division, which with its 20 million players
represents a major current commercial title. The approach
presented provides a mixed-methods framework, combining
qualitative knowledge elicitation and workshops with largescale
telemetry analysis, using sequence mining and clustering
to develop detailed player profiles showing the core gameplay
loops of The Division’s players.

Original language	English
Publication status	Accepted/In press - 2018
Event	Artificial Intelligence and Interactive Digital Entertainment Conference - Duration: 13 Nov 2018 → 17 Nov 2018 https://sites.google.com/ncsu.edu/aiide-2018/

Conference

Conference	Artificial Intelligence and Interactive Digital Entertainment Conference
Period	13/11/18 → 17/11/18
Internet address	https://sites.google.com/ncsu.edu/aiide-2018/

Bibliographical note

© 2018, Association for the Advancement of Artificial
Intelligence.

Access to Document

dna-string-sequence(1)
© 2018, Association for the Advancement of Artificial Intelligence.
Accepted author manuscript, 359 KBLicence: Unspecified

Cite this

@conference{6e0bf5e624db4b9782a9f733fa1b2162,

title = "Like a DNA string: Sequence-based Player Profiling in Tom Clancy{\textquoteright}s The Division",

abstract = "In this paper we present an approach for using sequence analysisto model player behavior. This approach is designedto work in game development contexts, integrating productionteams and delivering profiles that inform game design.We demonstrate the method via a case study of the gameTom Clancy{\textquoteright}s The Division, which with its 20 million playersrepresents a major current commercial title. The approachpresented provides a mixed-methods framework, combiningqualitative knowledge elicitation and workshops with largescaletelemetry analysis, using sequence mining and clusteringto develop detailed player profiles showing the core gameplayloops of The Division{\textquoteright}s players.",

author = "Sasha Makarovych and Alessandro Canossa and Julian Togelius and Anders Drachen",

note = "{\textcopyright} 2018, Association for the Advancement of Artificial Intelligence.; Artificial Intelligence and Interactive Digital Entertainment Conference ; Conference date: 13-11-2018 Through 17-11-2018",

year = "2018",

language = "English",

url = "https://sites.google.com/ncsu.edu/aiide-2018/",

}

TY - CONF

T1 - Like a DNA string

T2 - Artificial Intelligence and Interactive Digital Entertainment Conference

AU - Makarovych, Sasha

AU - Canossa, Alessandro

AU - Togelius, Julian

AU - Drachen, Anders

PY - 2018

Y1 - 2018

N2 - In this paper we present an approach for using sequence analysisto model player behavior. This approach is designedto work in game development contexts, integrating productionteams and delivering profiles that inform game design.We demonstrate the method via a case study of the gameTom Clancy’s The Division, which with its 20 million playersrepresents a major current commercial title. The approachpresented provides a mixed-methods framework, combiningqualitative knowledge elicitation and workshops with largescaletelemetry analysis, using sequence mining and clusteringto develop detailed player profiles showing the core gameplayloops of The Division’s players.

AB - In this paper we present an approach for using sequence analysisto model player behavior. This approach is designedto work in game development contexts, integrating productionteams and delivering profiles that inform game design.We demonstrate the method via a case study of the gameTom Clancy’s The Division, which with its 20 million playersrepresents a major current commercial title. The approachpresented provides a mixed-methods framework, combiningqualitative knowledge elicitation and workshops with largescaletelemetry analysis, using sequence mining and clusteringto develop detailed player profiles showing the core gameplayloops of The Division’s players.

M3 - Paper

Y2 - 13 November 2018 through 17 November 2018

ER -