Measurement and analysis of Gab, an unmoderated social network system

• Ano de defesa: 2019
• Autor(a) principal: Lucas Henrique Costa de Lima
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Universidade Federal de Minas Gerais; Brasil; ICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO; Programa de Pós-Graduação em Ciência da Computação; UFMG
• Palavras-chave em Português: Gab; Twitter; Social media; News; Hate speech; Computação – Teses; Gab– Teses; Twitter – Teses; Redes sociais – Teses; Discurso de ódio – Teses; Liberdade de expressão – Teses
• Link de acesso: http://hdl.handle.net/1843/50994

Social media systems have changed the way our society communicates, becoming popular places for users to consume, produce, and disseminate content. Despite the valuable social interactions that the online media promote, these systems also provide space for speech that would potentially be detrimental to different groups of people. Recently, there has been a long debate between content regulation and freedom of expression in social networks. The moderation of content in many social media systems, such as Twitter and Facebook, motivated the emergence of a new social network for free speech, named Gab. Soon after that, the Gab app has been removed from Google Play Store for violating the company's hate speech policy and it has been rejected by Apple for similar reasons. In this work, present a deep study about Gab, aiming at understanding who are the users who joined it and what kind of content they share in this system. Our findings show that Gab is a very politically oriented system that hosts banned users from other social networks, some of them due to possible cases of hate speech and association with extremism. We provide the first measurement of news dissemination inside a right-leaning echo chamber, investigating a social media where readers are rarely exposed to content that cuts across ideological lines, but rather are fed with content that reinforces their current beliefs. We present an analysis of posts from Gab, while comparing them with those from Twitter, a content-moderated social network. Our findings support that unmoderated environments have significant different linguistic features from moderated environments, and proportionally more hate speech. Finally, we show the most common type of hate in both social systems. We hope our analysis and findings may contribute to the discussion around moderation of speech and benefit hate speech detection approaches.