Analyzing Pokémon and Mario Streamers' Twitch Chat with LLM-based User Embeddings
This work provides a novel method for understanding viewer behavior in live streaming communities, though it is incremental in applying existing techniques to a new domain.
The study introduced a digital humanities approach using LLM-based user embeddings to analyze Twitch chat from three streamers, identifying shared chatter categories like supportive viewers and emoji senders, with repetitive spammers found in two streamers.
We present a novel digital humanities method for representing our Twitch chatters as user embeddings created by a large language model (LLM). We cluster these embeddings automatically using affinity propagation and further narrow this clustering down through manual analysis. We analyze the chat of one stream by each Twitch streamer: SmallAnt, DougDoug and PointCrow. Our findings suggest that each streamer has their own type of chatters, however two categories emerge for all of the streamers: supportive viewers and emoji and reaction senders. Repetitive message spammers is a shared chatter category for two of the streamers.