piwik-script

Deutsch Intern
    Data Science Chair

    Analysing Comments on Twitch.tv

    We have been working on analysing messages on the platform twitch.tv for a couple of years in cooperation with vAudience.

    We're running a crawler collecting millions of messages each month, for a total of a several terabytes of text data. We have also organised a shared task trying to predict the subscription status of users for channels.

    At the start of 2023, we will start a new project aiming to automatically moderate and enrich messages on Twitch and similar platforms.

    If you are interested in this topic, feel free to contact Albin!

    Publications

    • Towards Predicting the Su...
      Towards Predicting the Subscription Status of Twitch.tv Users Kobs, Konstantin; Potthast, Martin; Wiegmann, Matti; Zehe, Albin; Stein, Benno; Hotho, Andreas in Proceedings of ECML-PKDD 2020 ChAT Discovery Challenge on Chat Analytics for Twitch (2020).
    • Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels Kobs, Konstantin; Zehe, Albin; Bernstetter, Armin; Chibane, Julian; Pfister, Jan; Tritscher, Julian; Hotho, Andreas in {ACM} Transactions on Social Computing (2020). 3(2) 1–34.
    • Emote-Controlled: Obtaini...
      Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels Kobs, Konstantin; Zehe, Albin; Bernstetter, Armin; Chibane, Julian; Pfister, Jan; Tritscher, Julian; Hotho, Andreas in ACM Transactions on Social Computing (2020).