Murder mystery generation from open data

Gabriella A.B. Barros, Antonios Liapis, Julian Togelius

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    This paper describes a system for generating murder mysteries for adventure games, using associations between real-world people mined from Wikipedia articles. A game is seeded with a real-world person, and the game discovers suitable suspects for the murder of a game character instantiated from that person. Moreover, the game discovers characteristics of the suspects which can act as clues for the player to narrow down her search for the killer. The possible suspects and their characteristics are collected from Wikipedia articles and their linked data, while the best combination of suspects and characteristics for a murder mystery is found via evolutionary search. The paper includes an example murder mystery generated by the system revolving around the (hypothetical) death of a contemporary celebrity.

    Original languageEnglish (US)
    Title of host publicationProceedings of the 7th International Conference on Computational Creativity, ICCC 2016
    EditorsFrancois Pachet, F. Amilcar Cardoso, Vincent Corruble, Fiammetta Ghedini
    PublisherSony CSL
    Pages197-204
    Number of pages8
    ISBN (Electronic)9782746691551
    StatePublished - 2016
    Event7th International Conference on Computational Creativity, ICCC 2016 - Paris, France
    Duration: Jun 27 2016Jul 1 2016

    Publication series

    NameProceedings of the 7th International Conference on Computational Creativity, ICCC 2016

    Conference

    Conference7th International Conference on Computational Creativity, ICCC 2016
    Country/TerritoryFrance
    CityParis
    Period6/27/167/1/16

    ASJC Scopus subject areas

    • Computational Theory and Mathematics

    Fingerprint

    Dive into the research topics of 'Murder mystery generation from open data'. Together they form a unique fingerprint.

    Cite this