Modeling player experience for content creation

Christopher Pedersen, Julian Togelius, Georgios N. Yannakakis

    Research output: Contribution to journalArticle

    Abstract

    In this paper, we use computational intelligence techniques to built quantitative models of player experience for a platform game. The models accurately predict certain key affective states of the player based on both gameplay metrics that relate to the actions performed by the player in the game, and on parameters of the level that was played. For the experiments presented here, a version of the classic Super Mario Bros game is enhanced with parameterizable level generation and gameplay metrics collection. Player pairwise preference data is collected using forced choice questionnaires, and the models are trained using this data and neuroevolutionary preference learning of multilayer perceptrons (MLPs). The derived models will be used to optimize design parameters for particular types of player experience, allowing the designer to automatically generate unique levels that induce the desired experience for the player.

    Original languageEnglish (US)
    Article number5420018
    Pages (from-to)54-67
    Number of pages14
    JournalIEEE Transactions on Computational Intelligence and AI in Games
    Volume2
    Issue number1
    DOIs
    StatePublished - Mar 2010

    Fingerprint

    Multilayer neural networks
    Artificial intelligence
    Experiments

    Keywords

    • Content creation
    • Fun
    • Neuroevolution
    • Platform games
    • Player experience
    • Player satisfaction modeling
    • Preference learning

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software
    • Control and Systems Engineering
    • Electrical and Electronic Engineering

    Cite this

    Modeling player experience for content creation. / Pedersen, Christopher; Togelius, Julian; Yannakakis, Georgios N.

    In: IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2, No. 1, 5420018, 03.2010, p. 54-67.

    Research output: Contribution to journalArticle

    Pedersen, Christopher ; Togelius, Julian ; Yannakakis, Georgios N. / Modeling player experience for content creation. In: IEEE Transactions on Computational Intelligence and AI in Games. 2010 ; Vol. 2, No. 1. pp. 54-67.
    @article{28c23ef575ff497f901c108cfb4160ee,
    title = "Modeling player experience for content creation",
    abstract = "In this paper, we use computational intelligence techniques to built quantitative models of player experience for a platform game. The models accurately predict certain key affective states of the player based on both gameplay metrics that relate to the actions performed by the player in the game, and on parameters of the level that was played. For the experiments presented here, a version of the classic Super Mario Bros game is enhanced with parameterizable level generation and gameplay metrics collection. Player pairwise preference data is collected using forced choice questionnaires, and the models are trained using this data and neuroevolutionary preference learning of multilayer perceptrons (MLPs). The derived models will be used to optimize design parameters for particular types of player experience, allowing the designer to automatically generate unique levels that induce the desired experience for the player.",
    keywords = "Content creation, Fun, Neuroevolution, Platform games, Player experience, Player satisfaction modeling, Preference learning",
    author = "Christopher Pedersen and Julian Togelius and Yannakakis, {Georgios N.}",
    year = "2010",
    month = "3",
    doi = "10.1109/TCIAIG.2010.2043950",
    language = "English (US)",
    volume = "2",
    pages = "54--67",
    journal = "IEEE Transactions on Computational Intelligence and AI in Games",
    issn = "1943-068X",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "1",

    }

    TY - JOUR

    T1 - Modeling player experience for content creation

    AU - Pedersen, Christopher

    AU - Togelius, Julian

    AU - Yannakakis, Georgios N.

    PY - 2010/3

    Y1 - 2010/3

    N2 - In this paper, we use computational intelligence techniques to built quantitative models of player experience for a platform game. The models accurately predict certain key affective states of the player based on both gameplay metrics that relate to the actions performed by the player in the game, and on parameters of the level that was played. For the experiments presented here, a version of the classic Super Mario Bros game is enhanced with parameterizable level generation and gameplay metrics collection. Player pairwise preference data is collected using forced choice questionnaires, and the models are trained using this data and neuroevolutionary preference learning of multilayer perceptrons (MLPs). The derived models will be used to optimize design parameters for particular types of player experience, allowing the designer to automatically generate unique levels that induce the desired experience for the player.

    AB - In this paper, we use computational intelligence techniques to built quantitative models of player experience for a platform game. The models accurately predict certain key affective states of the player based on both gameplay metrics that relate to the actions performed by the player in the game, and on parameters of the level that was played. For the experiments presented here, a version of the classic Super Mario Bros game is enhanced with parameterizable level generation and gameplay metrics collection. Player pairwise preference data is collected using forced choice questionnaires, and the models are trained using this data and neuroevolutionary preference learning of multilayer perceptrons (MLPs). The derived models will be used to optimize design parameters for particular types of player experience, allowing the designer to automatically generate unique levels that induce the desired experience for the player.

    KW - Content creation

    KW - Fun

    KW - Neuroevolution

    KW - Platform games

    KW - Player experience

    KW - Player satisfaction modeling

    KW - Preference learning

    UR - http://www.scopus.com/inward/record.url?scp=77954986325&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77954986325&partnerID=8YFLogxK

    U2 - 10.1109/TCIAIG.2010.2043950

    DO - 10.1109/TCIAIG.2010.2043950

    M3 - Article

    VL - 2

    SP - 54

    EP - 67

    JO - IEEE Transactions on Computational Intelligence and AI in Games

    JF - IEEE Transactions on Computational Intelligence and AI in Games

    SN - 1943-068X

    IS - 1

    M1 - 5420018

    ER -