Modelling the socio-linguistic evolution of extremist groups

Speaker: Dr Christine de Kock (Assistant professor in the School for Computing and Information Systems at the University of Melbourne)

Pricing

• Free

Dates and Times

Contact

Kristen Moore

More information

Abstract:

Group dynamics are often revealed through subtle changes in the language and the social ties of a community. This is especially true in the context of extremist groups: vocabularies mutate at high rates to evade filters, and social graphs fragment to create splinter-groups that tend towards increasing radicalism. These dynamics expose key shortcomings in current natural language processing technologies, e.g. large language models (LLMs), especially when used for content moderation. In this talk, I will describe recent methods, datasets, and models we developed to address these challenges. Our experiments center on two online extremist platforms, Incels and Stormfront, which promote alt-right and misogynistic ideologies, respectively.

Bio:

Dr Christine de Kock is an assistant professor in the School for Computing and Information Systems at the University of Melbourne. Her research explores topics in computational sociolinguistics, with a particular focus on harmful online behaviour. She completed her PhD in the Natural Language and Information Processing group at Cambridge.