Spread of Hate Speech in Online Social Media

Abstract

The present online social media platform is afflicted with several issues, with hate speech being on the predominant forefront. The prevalence of online hate speech has fuelled horrific real-world hate-crime such as the mass-genocide of Rohingya Muslims, communal violence in Colombo and the recent massacre in the Pittsburgh synagogue. Consequently, It is imperative to understand the diffusion of such hateful content in an online setting. We conduct the first study that analyses the flow and dynamics of posts generated by hateful and non-hateful users on Gab (gab.com) over a massive dataset of 341K users and 21M posts. Our observations confirms that hateful content diffuse farther, wider and faster and have a greater outreach than those of non-hateful users. A deeper inspection into the profiles and network of hateful and nonhateful users reveals that the former are more influential, popular and cohesive. Thus, our research explores the interesting facets of diffusion dynamics of hateful users and broadens our understanding of hate speech in the online world.

Automated Amharic Hate Speech Posts and Comments Detection Model Using Recurrent Neural Network

“…Generally, LSTM can retain the knowledge of earlier states to be trained for tasks that require large memory or state awareness of tasks due to this reason it can overcome the limitation of RNN because it consists block of memory cells state by which signal flows by regulating input, forget and output gates to control what is stored, read and written on cell. LSTM is used by Google, Apple, and Amazon [23].…”

Hate Contagion: Measuring the spread and trajectory of hate on social media

“…In the context of extremist content, these online social contagion effects have been shown both for Islamic extremist and far-right material (Ferrara, 2017;Mathew et al, 2019). By mapping the spread of propaganda, influential Islamic extremist supporters on Twitter were shown to influence other previously non-supportive users, with the average Islamic extremist "infecting" 2.13 other users before being suspended (Ferrara, 2017).…”

“…By mapping the spread of propaganda, influential Islamic extremist supporters on Twitter were shown to influence other previously non-supportive users, with the average Islamic extremist "infecting" 2.13 other users before being suspended (Ferrara, 2017). On far-right platforms, users expressing hate speech were shown to instigate larger information cascades than non-hateful users, indicating that these users are more likely to 'go viral' on the platform (Mathew et al, 2019). However, in these cases, contagion was measured by the successful propagation of extreme content, which may be biased by a number of factors such as user popularity, relative activity of more extreme users, and prevalence of this content.…”

“…Online hate typically takes the form of verbal or written attacks against a specific group of people focused on, or motivated by, certain aspects of that group's identity (Davidson, Warmsley, Macy, & Weber, 2017;de Gibert, Perez, García-Pablos, & Cuadros, 2018;Gallacher, 2021). Hate speech is particularly common in expressions shared by the far-right, both within traditional right-wing extremist groups and the more recent 'alt-right' movements (Mathew, Dutt, Goyal, & Mukherjee, 2019;Vidgen, Yasseri, & Margetts, 2019). These far-right groups are broadly defined by holding ideals of racial and ethnic nationalism, and typically framed in terms of white power and/or white identity; this forms the ingroup.…”

Online Xenophobic Behavior Amid the COVID-19 Pandemic

“…The analysis and detection of online xenophobic behaviors such as hate speeches [10,24] has been widely studied by the social, computer, and data science research community. The spread of antisocial behaviors in social media has not only sown discord among individuals or communities online but also has resulted in violent hate crimes [17,22,30]. Therefore, it is a pressing issue to detect and curb online antisocial behaviors, particularly during a pandemic, where preventing such undesirable online behaviors can avoid adding problems to the already difficult crisis.…”