Jointly modelling the evolution of social structure and language in online communities

TL;DR

This paper introduces a joint model for capturing the evolution of social structures and language in online communities, enabling better analysis of group dynamics, interests, and language use over time.

Contribution

It presents a novel method that jointly models community structure and language evolution, outperforming previous models that considered only one aspect.

Findings

Outperforms prior models in clustering and embedding prediction tasks.

Enables analysis of group responses to temporal events.

Quantifies propensity for violent language in extremist groups.

Abstract

Group interactions take place within a particular socio-temporal context, which should be taken into account when modelling interactions in online communities. We propose a method for jointly modelling community structure and language over time. Our system produces dynamic word and user representations that can be used to cluster users, investigate thematic interests of groups, and predict group membership. We apply and evaluate our method in the context of a set of misogynistic extremist groups. Our results indicate that this approach outperforms prior models which lacked one of these components (i.e. not incorporating social structure, or using static word embeddings) when evaluated on clustering and embedding prediction tasks. Our method further enables novel types of analyses on online groups, including tracing their response to temporal events and quantifying their propensity for using violent language, which is of particular importance in the context of extremist groups.