Efficiently detecting outlying behavior in video-game players

Young Bin Kim, Shin Jin Kang, Sang Hyeok Lee, Jang Young Jung, Hyeong Ryeol Kam, Jung Lee, Young Sun Kim, Joonsoo Lee, Chang-Hun Kim

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, we propose a method for automatically detecting the times during which game players exhibit specific behavior, such as when players commonly show excitement, concentration, immersion, and surprise. The proposed method detects such outlying behavior based on the game players' characteristics. These characteristics are captured non-invasively in a general game environment. In this paper, cameras were used to analyze observed data such as facial expressions and player movements.Moreover, multimodal data from the game players (i.e., data regarding adjustments to the volume and the use of the keyboard and mouse) was used to analyze high-dimensional game-player data. A support vector machine was used to efficiently detect outlying behaviors. We verified the effectiveness of the proposed method using games from several genres. The recall rate of the outlying behavior pre-identified by industry experts was approximately 70%. The proposed method can also be used for feedback analysis of various interactive content provided in PC environments.

Original languageEnglish
Article numbere1502
JournalPeerJ
Volume2015
Issue number12
DOIs
Publication statusPublished - 2015

Fingerprint

Video Games
Support vector machines
Cameras
Feedback
Industry
keyboards
Facial Expression
Immersion
methodology
cameras
Research Design
industry
mice

Keywords

  • Game environments
  • Outlier detection
  • User behavior analysis

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)
  • Neuroscience(all)

Cite this

Kim, Y. B., Kang, S. J., Lee, S. H., Jung, J. Y., Kam, H. R., Lee, J., ... Kim, C-H. (2015). Efficiently detecting outlying behavior in video-game players. PeerJ, 2015(12), [e1502]. https://doi.org/10.7717/peerj.1502

Efficiently detecting outlying behavior in video-game players. / Kim, Young Bin; Kang, Shin Jin; Lee, Sang Hyeok; Jung, Jang Young; Kam, Hyeong Ryeol; Lee, Jung; Kim, Young Sun; Lee, Joonsoo; Kim, Chang-Hun.

In: PeerJ, Vol. 2015, No. 12, e1502, 2015.

Research output: Contribution to journalArticle

Kim, YB, Kang, SJ, Lee, SH, Jung, JY, Kam, HR, Lee, J, Kim, YS, Lee, J & Kim, C-H 2015, 'Efficiently detecting outlying behavior in video-game players', PeerJ, vol. 2015, no. 12, e1502. https://doi.org/10.7717/peerj.1502
Kim YB, Kang SJ, Lee SH, Jung JY, Kam HR, Lee J et al. Efficiently detecting outlying behavior in video-game players. PeerJ. 2015;2015(12). e1502. https://doi.org/10.7717/peerj.1502
Kim, Young Bin ; Kang, Shin Jin ; Lee, Sang Hyeok ; Jung, Jang Young ; Kam, Hyeong Ryeol ; Lee, Jung ; Kim, Young Sun ; Lee, Joonsoo ; Kim, Chang-Hun. / Efficiently detecting outlying behavior in video-game players. In: PeerJ. 2015 ; Vol. 2015, No. 12.
@article{efd7fb61b5924eedb6063f2ab436a6a1,
title = "Efficiently detecting outlying behavior in video-game players",
abstract = "In this paper, we propose a method for automatically detecting the times during which game players exhibit specific behavior, such as when players commonly show excitement, concentration, immersion, and surprise. The proposed method detects such outlying behavior based on the game players' characteristics. These characteristics are captured non-invasively in a general game environment. In this paper, cameras were used to analyze observed data such as facial expressions and player movements.Moreover, multimodal data from the game players (i.e., data regarding adjustments to the volume and the use of the keyboard and mouse) was used to analyze high-dimensional game-player data. A support vector machine was used to efficiently detect outlying behaviors. We verified the effectiveness of the proposed method using games from several genres. The recall rate of the outlying behavior pre-identified by industry experts was approximately 70{\%}. The proposed method can also be used for feedback analysis of various interactive content provided in PC environments.",
keywords = "Game environments, Outlier detection, User behavior analysis",
author = "Kim, {Young Bin} and Kang, {Shin Jin} and Lee, {Sang Hyeok} and Jung, {Jang Young} and Kam, {Hyeong Ryeol} and Jung Lee and Kim, {Young Sun} and Joonsoo Lee and Chang-Hun Kim",
year = "2015",
doi = "10.7717/peerj.1502",
language = "English",
volume = "2015",
journal = "PeerJ",
issn = "2167-8359",
publisher = "PeerJ",
number = "12",

}

TY - JOUR

T1 - Efficiently detecting outlying behavior in video-game players

AU - Kim, Young Bin

AU - Kang, Shin Jin

AU - Lee, Sang Hyeok

AU - Jung, Jang Young

AU - Kam, Hyeong Ryeol

AU - Lee, Jung

AU - Kim, Young Sun

AU - Lee, Joonsoo

AU - Kim, Chang-Hun

PY - 2015

Y1 - 2015

N2 - In this paper, we propose a method for automatically detecting the times during which game players exhibit specific behavior, such as when players commonly show excitement, concentration, immersion, and surprise. The proposed method detects such outlying behavior based on the game players' characteristics. These characteristics are captured non-invasively in a general game environment. In this paper, cameras were used to analyze observed data such as facial expressions and player movements.Moreover, multimodal data from the game players (i.e., data regarding adjustments to the volume and the use of the keyboard and mouse) was used to analyze high-dimensional game-player data. A support vector machine was used to efficiently detect outlying behaviors. We verified the effectiveness of the proposed method using games from several genres. The recall rate of the outlying behavior pre-identified by industry experts was approximately 70%. The proposed method can also be used for feedback analysis of various interactive content provided in PC environments.

AB - In this paper, we propose a method for automatically detecting the times during which game players exhibit specific behavior, such as when players commonly show excitement, concentration, immersion, and surprise. The proposed method detects such outlying behavior based on the game players' characteristics. These characteristics are captured non-invasively in a general game environment. In this paper, cameras were used to analyze observed data such as facial expressions and player movements.Moreover, multimodal data from the game players (i.e., data regarding adjustments to the volume and the use of the keyboard and mouse) was used to analyze high-dimensional game-player data. A support vector machine was used to efficiently detect outlying behaviors. We verified the effectiveness of the proposed method using games from several genres. The recall rate of the outlying behavior pre-identified by industry experts was approximately 70%. The proposed method can also be used for feedback analysis of various interactive content provided in PC environments.

KW - Game environments

KW - Outlier detection

KW - User behavior analysis

UR - http://www.scopus.com/inward/record.url?scp=84951142771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951142771&partnerID=8YFLogxK

U2 - 10.7717/peerj.1502

DO - 10.7717/peerj.1502

M3 - Article

AN - SCOPUS:84951142771

VL - 2015

JO - PeerJ

JF - PeerJ

SN - 2167-8359

IS - 12

M1 - e1502

ER -