On Simulating the Propagation and Countermeasures of Hate Speech in Social Networks

Hate speech expresses prejudice and discrimination based on actual or perceived innate characteristics such as gender, race, religion, ethnicity, colour, national origin, disability sexual orientation. Research has proven that the amount of hateful messages increases inevitably online social media. Although hate propagators constitute a tiny minority—with less than 1% participants—they create an unproportionally high motivated content. Thus, if not countered properly, can propagate through whole society. In this paper we apply agent-based modelling to reproduce how phenomenon spreads within networks. We reuse insights from research literature construct validate baseline model for propagation speech. From this, three countermeasures are modelled simulated investigate their effectiveness in containing spread hatred: Education, deferring content, cyber activism. Our simulations suggest that: (1) Education consititutes very successful countermeasure, but it is long term still cannot eliminate hatred completely; (2) Deferring content similar—although lower—positive effect education, advantage being short-term countermeasure; (3) our simulations, extreme activism against shows poorest performance since seems increase likelihood resulting highly polarised societies.