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 Subscription Status of Twitch.tv Users 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 in {ACM} Transactions on Social Computing (2020). 3(2) 1–34.
-
Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels in ACM Transactions on Social Computing (2020).