Identifying Linguistically Relevant Communities of Practice on Twitch
Proceedings of the 1st Workshop on Social Context (SoCon) and the 2nd Workshop on Integrating NLP and Psychology to Study Social Interactions (NLPSI) @ LREC 2026
Abstract
This paper argues that, when it comes to modeling language variation and change on the video game streaming platform Twitch, it is necessary to consider "meso-level" communities of practice, i.e. communities of practice that are smaller than the full video game community, yet larger than the usual level of analysis in recent linguistics studies: communities associated with individual Twitch channels. We present a computational method for identifying these linguistically relevant communities of practice and show how this method can be useful for analyzing quantitative patterns of sociolinguistic variation in a corpus composed of the chat transcripts of 15 streamers of the game Elden Ring: Nightreign.