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

    Keywords

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

    ASJC Scopus subject areas

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

    Fingerprint Dive into the research topics of 'Detecting Predatory Behavior in Game Chats'. Together they form a unique fingerprint.

  • 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