• Acquisition and Analysis of a Meme Corpus to Investigate Web Culture

    Author(s):
    Thomas Fischer, Philipp Hartl, Andreas Hilzenthaler, Dominik Ramsauer, Thomas Schmidt (see profile) , Christian Wolff
    Date:
    2020
    Group(s):
    DH2020
    Subject(s):
    Corpus, Internet culture, Internet memes, Media studies, Social media, Text analytics
    Item Type:
    Other
    Tag(s):
    sentiment analysis, text mining, topic modeling, web culture
    Permanent URL:
    http://dx.doi.org/10.17613/mw0s-0805
    Abstract:
    Memes are a popular part of today’s online culture reflecting current developments in pop-culture, politics or sports and are created and shared in large scale on a daily basis. We present first results of an ongoing project about the study of online-memes via computational Distant Reading methods. We focus on the meme type of image macros. Image macros memes consists of a reusable image template with a top and/or bottom text and are the most common and popular meme types. We gather a corpus for 16 of the most popular image macros memes by crawling the platform knowyourmeme.com thus creating a corpus consisting of 7840 memes incarnations and their corresponding metadata. Furthermore, we gather the text of the memes via OCR and make this corpus publicly available for the research community. We explore the application of various text mining methods like Topic Modeling and Sentiment Analysis to analyze the language, the topics and the moods expressed via online memes.
    Notes:
    Poster contribution to the Digital Humanities Conferene 2020 (DH 2020). You can find the corresponding paper contribution here: https://www.dropbox.com/s/fms9238b2ftr91l/DH2020_Memes_Abstract.pdf
    Metadata:
    Status:
    Published
    Last Updated:
    4 months ago
    License:
    Attribution
    Share this:

    Downloads

    Item Name:pdf dh2020_memes_poster.pdf
     Download View in browser
    Activity: Downloads: 108