Predicting MMO Player Gender from In-Game Attributes Using Machine Learning Models

Tracy Kennedy, Rabindra (Robby) Ratan, Komal Kapoor, Nishith Pathak, Dmitri Williams, Jaideep Srivastava

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

What in-game attributes predict players’ offline gender? Our research addresses this question using behavioral logs of over 4,000 EverQuest II players. The analysis compares four variable sets with multiple combinations of character types (avatar characteristics or gameplay behaviors; primary or nonprimary character), three server types within the game (roleplaying, player-vs-player, and player-vs-environment), and three types of predictive machine learning models (JRip, J48, and Random Tree). Overall, the most highly predictive, interpretable model has an f-measure of 0.94 and suggests the primary character gender and number of male and female characters a player has provide the most prediction value, with players choosing characters to match their own gender. The results also suggest that female players craft, scribe recipes, and harvest items more than male players. While the strength of these findings varies by server type, they are generally consistent with previous research and suggest that players tend to play in ways that are consistent with their offline identities.

Original languageEnglish
Title of host publicationSpringer Proceedings in Complexity
PublisherSpringer
Pages69-84
Number of pages16
VolumePart F3
DOIs
Publication statusPublished - 1 Jan 2014
Externally publishedYes

Fingerprint

Learning systems
Machine Learning
Servers
Attribute
Game
Server
Random Trees
Avatar
Model
Predictive Model
Gender
Character
Vary
Tend
Predict
Prediction

Keywords

  • Gender in MMOs
  • Gender prediction
  • Machine learning models
  • MMOs

ASJC Scopus subject areas

  • Applied Mathematics
  • Modelling and Simulation
  • Computer Science Applications

Cite this

Kennedy, T., Ratan, R. R., Kapoor, K., Pathak, N., Williams, D., & Srivastava, J. (2014). Predicting MMO Player Gender from In-Game Attributes Using Machine Learning Models. In Springer Proceedings in Complexity (Vol. Part F3, pp. 69-84). Springer. https://doi.org/10.1007/978-3-319-07142-8_5

Predicting MMO Player Gender from In-Game Attributes Using Machine Learning Models. / Kennedy, Tracy; Ratan, Rabindra (Robby); Kapoor, Komal; Pathak, Nishith; Williams, Dmitri; Srivastava, Jaideep.

Springer Proceedings in Complexity. Vol. Part F3 Springer, 2014. p. 69-84.

Research output: Chapter in Book/Report/Conference proceedingChapter

Kennedy, T, Ratan, RR, Kapoor, K, Pathak, N, Williams, D & Srivastava, J 2014, Predicting MMO Player Gender from In-Game Attributes Using Machine Learning Models. in Springer Proceedings in Complexity. vol. Part F3, Springer, pp. 69-84. https://doi.org/10.1007/978-3-319-07142-8_5
Kennedy T, Ratan RR, Kapoor K, Pathak N, Williams D, Srivastava J. Predicting MMO Player Gender from In-Game Attributes Using Machine Learning Models. In Springer Proceedings in Complexity. Vol. Part F3. Springer. 2014. p. 69-84 https://doi.org/10.1007/978-3-319-07142-8_5
Kennedy, Tracy ; Ratan, Rabindra (Robby) ; Kapoor, Komal ; Pathak, Nishith ; Williams, Dmitri ; Srivastava, Jaideep. / Predicting MMO Player Gender from In-Game Attributes Using Machine Learning Models. Springer Proceedings in Complexity. Vol. Part F3 Springer, 2014. pp. 69-84
@inbook{7aa797862eef464484c8c9a12207b292,
title = "Predicting MMO Player Gender from In-Game Attributes Using Machine Learning Models",
abstract = "What in-game attributes predict players’ offline gender? Our research addresses this question using behavioral logs of over 4,000 EverQuest II players. The analysis compares four variable sets with multiple combinations of character types (avatar characteristics or gameplay behaviors; primary or nonprimary character), three server types within the game (roleplaying, player-vs-player, and player-vs-environment), and three types of predictive machine learning models (JRip, J48, and Random Tree). Overall, the most highly predictive, interpretable model has an f-measure of 0.94 and suggests the primary character gender and number of male and female characters a player has provide the most prediction value, with players choosing characters to match their own gender. The results also suggest that female players craft, scribe recipes, and harvest items more than male players. While the strength of these findings varies by server type, they are generally consistent with previous research and suggest that players tend to play in ways that are consistent with their offline identities.",
keywords = "Gender in MMOs, Gender prediction, Machine learning models, MMOs",
author = "Tracy Kennedy and Ratan, {Rabindra (Robby)} and Komal Kapoor and Nishith Pathak and Dmitri Williams and Jaideep Srivastava",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/978-3-319-07142-8_5",
language = "English",
volume = "Part F3",
pages = "69--84",
booktitle = "Springer Proceedings in Complexity",
publisher = "Springer",

}

TY - CHAP

T1 - Predicting MMO Player Gender from In-Game Attributes Using Machine Learning Models

AU - Kennedy, Tracy

AU - Ratan, Rabindra (Robby)

AU - Kapoor, Komal

AU - Pathak, Nishith

AU - Williams, Dmitri

AU - Srivastava, Jaideep

PY - 2014/1/1

Y1 - 2014/1/1

N2 - What in-game attributes predict players’ offline gender? Our research addresses this question using behavioral logs of over 4,000 EverQuest II players. The analysis compares four variable sets with multiple combinations of character types (avatar characteristics or gameplay behaviors; primary or nonprimary character), three server types within the game (roleplaying, player-vs-player, and player-vs-environment), and three types of predictive machine learning models (JRip, J48, and Random Tree). Overall, the most highly predictive, interpretable model has an f-measure of 0.94 and suggests the primary character gender and number of male and female characters a player has provide the most prediction value, with players choosing characters to match their own gender. The results also suggest that female players craft, scribe recipes, and harvest items more than male players. While the strength of these findings varies by server type, they are generally consistent with previous research and suggest that players tend to play in ways that are consistent with their offline identities.

AB - What in-game attributes predict players’ offline gender? Our research addresses this question using behavioral logs of over 4,000 EverQuest II players. The analysis compares four variable sets with multiple combinations of character types (avatar characteristics or gameplay behaviors; primary or nonprimary character), three server types within the game (roleplaying, player-vs-player, and player-vs-environment), and three types of predictive machine learning models (JRip, J48, and Random Tree). Overall, the most highly predictive, interpretable model has an f-measure of 0.94 and suggests the primary character gender and number of male and female characters a player has provide the most prediction value, with players choosing characters to match their own gender. The results also suggest that female players craft, scribe recipes, and harvest items more than male players. While the strength of these findings varies by server type, they are generally consistent with previous research and suggest that players tend to play in ways that are consistent with their offline identities.

KW - Gender in MMOs

KW - Gender prediction

KW - Machine learning models

KW - MMOs

UR - http://www.scopus.com/inward/record.url?scp=85052384462&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052384462&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-07142-8_5

DO - 10.1007/978-3-319-07142-8_5

M3 - Chapter

VL - Part F3

SP - 69

EP - 84

BT - Springer Proceedings in Complexity

PB - Springer

ER -