Detecting Predatory Behavior in Game Chats

Yun Gyung Cheong, Alaina K. Jensen, Elin Rut Gudnadottir, Byung Chull Bae, Julian Togelius

    Research output: Contribution to journalArticle

    Abstract

    While games are a popular social media for children, there is a real risk that these children are exposed to potential sexual assault. A number of studies have already addressed this issue, however, the data used in previous research did not properly represent the real chats found in multiplayer online games. To address this issue, we obtained real chat data from MovieStarPlanet, a massively multiplayer online game for children. The research described in this paper aimed to detect predatory behaviors in the chats using machine learning methods. In order to achieve a high accuracy on this task, extensive preprocessing was necessary. We describe three different strategies for data selection and preprocessing, and extensively compare the performance of different learning algorithms on the different data sets and features.

    Original languageEnglish (US)
    Article number7091007
    Pages (from-to)220-232
    Number of pages13
    JournalIEEE Transactions on Computational Intelligence and AI in Games
    Volume7
    Issue number3
    DOIs
    StatePublished - Sep 1 2015

    Fingerprint

    Learning algorithms
    Learning systems

    Keywords

    • Chat
    • data mining
    • game data
    • natural language processing (NLP)
    • preprocessing
    • sexual predator
    • text classification

    ASJC Scopus subject areas

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

    Cite this

    Cheong, Y. G., Jensen, A. K., Gudnadottir, E. R., Bae, B. C., & Togelius, J. (2015). Detecting Predatory Behavior in Game Chats. IEEE Transactions on Computational Intelligence and AI in Games, 7(3), 220-232. [7091007]. https://doi.org/10.1109/TCIAIG.2015.2424932

    Detecting Predatory Behavior in Game Chats. / Cheong, Yun Gyung; Jensen, Alaina K.; Gudnadottir, Elin Rut; Bae, Byung Chull; Togelius, Julian.

    In: IEEE Transactions on Computational Intelligence and AI in Games, Vol. 7, No. 3, 7091007, 01.09.2015, p. 220-232.

    Research output: Contribution to journalArticle

    Cheong, YG, Jensen, AK, Gudnadottir, ER, Bae, BC & Togelius, J 2015, 'Detecting Predatory Behavior in Game Chats', IEEE Transactions on Computational Intelligence and AI in Games, vol. 7, no. 3, 7091007, pp. 220-232. https://doi.org/10.1109/TCIAIG.2015.2424932
    Cheong, Yun Gyung ; Jensen, Alaina K. ; Gudnadottir, Elin Rut ; Bae, Byung Chull ; Togelius, Julian. / Detecting Predatory Behavior in Game Chats. In: IEEE Transactions on Computational Intelligence and AI in Games. 2015 ; Vol. 7, No. 3. pp. 220-232.
    @article{0c3d2881be734c199f0e37904e0e4e87,
    title = "Detecting Predatory Behavior in Game Chats",
    abstract = "While games are a popular social media for children, there is a real risk that these children are exposed to potential sexual assault. A number of studies have already addressed this issue, however, the data used in previous research did not properly represent the real chats found in multiplayer online games. To address this issue, we obtained real chat data from MovieStarPlanet, a massively multiplayer online game for children. The research described in this paper aimed to detect predatory behaviors in the chats using machine learning methods. In order to achieve a high accuracy on this task, extensive preprocessing was necessary. We describe three different strategies for data selection and preprocessing, and extensively compare the performance of different learning algorithms on the different data sets and features.",
    keywords = "Chat, data mining, game data, natural language processing (NLP), preprocessing, sexual predator, text classification",
    author = "Cheong, {Yun Gyung} and Jensen, {Alaina K.} and Gudnadottir, {Elin Rut} and Bae, {Byung Chull} and Julian Togelius",
    year = "2015",
    month = "9",
    day = "1",
    doi = "10.1109/TCIAIG.2015.2424932",
    language = "English (US)",
    volume = "7",
    pages = "220--232",
    journal = "IEEE Transactions on Computational Intelligence and AI in Games",
    issn = "1943-068X",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "3",

    }

    TY - JOUR

    T1 - Detecting Predatory Behavior in Game Chats

    AU - Cheong, Yun Gyung

    AU - Jensen, Alaina K.

    AU - Gudnadottir, Elin Rut

    AU - Bae, Byung Chull

    AU - Togelius, Julian

    PY - 2015/9/1

    Y1 - 2015/9/1

    N2 - While games are a popular social media for children, there is a real risk that these children are exposed to potential sexual assault. A number of studies have already addressed this issue, however, the data used in previous research did not properly represent the real chats found in multiplayer online games. To address this issue, we obtained real chat data from MovieStarPlanet, a massively multiplayer online game for children. The research described in this paper aimed to detect predatory behaviors in the chats using machine learning methods. In order to achieve a high accuracy on this task, extensive preprocessing was necessary. We describe three different strategies for data selection and preprocessing, and extensively compare the performance of different learning algorithms on the different data sets and features.

    AB - While games are a popular social media for children, there is a real risk that these children are exposed to potential sexual assault. A number of studies have already addressed this issue, however, the data used in previous research did not properly represent the real chats found in multiplayer online games. To address this issue, we obtained real chat data from MovieStarPlanet, a massively multiplayer online game for children. The research described in this paper aimed to detect predatory behaviors in the chats using machine learning methods. In order to achieve a high accuracy on this task, extensive preprocessing was necessary. We describe three different strategies for data selection and preprocessing, and extensively compare the performance of different learning algorithms on the different data sets and features.

    KW - Chat

    KW - data mining

    KW - game data

    KW - natural language processing (NLP)

    KW - preprocessing

    KW - sexual predator

    KW - text classification

    UR - http://www.scopus.com/inward/record.url?scp=84959218843&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84959218843&partnerID=8YFLogxK

    U2 - 10.1109/TCIAIG.2015.2424932

    DO - 10.1109/TCIAIG.2015.2424932

    M3 - Article

    AN - SCOPUS:84959218843

    VL - 7

    SP - 220

    EP - 232

    JO - IEEE Transactions on Computational Intelligence and AI in Games

    JF - IEEE Transactions on Computational Intelligence and AI in Games

    SN - 1943-068X

    IS - 3

    M1 - 7091007

    ER -