Analyzing Pok\'emon and Mario Streamers' Twitch Chat with LLM-based User Embeddings

TL;DR

This paper introduces a novel method using large language models to create user embeddings from Twitch chat data, enabling analysis of viewer types and behaviors across different streamers.

Contribution

It presents a new digital humanities approach for representing and analyzing Twitch chatters with LLM-based embeddings and clustering techniques.

Findings

Each streamer has unique viewer types.

Supportive viewers and emoji senders are common categories.

Repetitive message spammers are identified in some streams.

Abstract

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.