piwik-script

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...
      Kobs, K., Potthast, M., Wiegmann, M., Zehe, A., Stein, B., Hotho, A.: Towards Predicting the Subscription Status of Twitch.tv Users. Proceedings of ECML-PKDD 2020 ChAT Discovery Challenge on Chat Analytics for Twitch. (2020).
    • Kobs, K., Zehe, A., Bernstetter, A., Chibane, J., Pfister, J., Tritscher, J., Hotho, A.: Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels. {ACM} Transactions on Social Computing. 3, 1–34 (2020).
    • Emote-Controlled: Obtaini...
      Kobs, K., Zehe, A., Bernstetter, A., Chibane, J., Pfister, J., Tritscher, J., Hotho, A.: Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels. ACM Transactions on Social Computing. (2020).