Analyzing information dissemination in publicly accessible politically oriented WhatsApp groups

• Autor(a) principal: Gustavo Jota Resende
• Data de Publicação: 2019
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Institucional da UFMG
• Texto Completo: http://hdl.handle.net/1843/56374
• topic: WhatsApp groups; Misinformation; Information dissemination; Images; Tex- tual information; Computação – Teses; WhatsApp (Aplicativo de mensagens) – Teses; Desinformação – Teses; Disseminação de informação – Teses.

WhatsApp has revolutionized the way people communicate and interact. It is not only cheaper than the traditional Short Message Service (SMS) communication but it also brings a new form of mobile communication: the group chats. Such groups are great forums for collective discussions on a variety of topics. In particular, in events of great social mobilization, such as electoral campaigns, WhatsApp group chats are very attractive as they facilitate information exchange among interested people. Yet, recent events in several countries have highlighted the use of WhatsApp to spread messages with false and misleading content, raising concerns about the massive use of this platform. This master thesis analyzes information dissemination within WhatsApp, focusing on publicly accessible political-oriented groups, collecting all shared messages during the 2018 Brazilian presidential campaign. Our study relied on a dataset containing images and textual messages shared in political groups during the study period. We identified the presence of misinformation in the contents of these messages using a dataset of priorly checked misinformation from six Brazilian fact-checking sites. From this evidence, our study aims to identify characteristics that distinguish messages (image and textual) with proven false content from other messages (with unverified content). To that end, we analyzed various properties of the images(e.g., main content, main image sources, and propagation from/to other Web platforms) and of the textual content (e.g., language usage, main topics and sentiment of message’s content), propagation dynamics and network structure of both message sets. We identify the most important sources of the fake images and found that they much more often appear first on WhatsApp and then on the Web. Our analyses also revealed that textual messages with misinformation tend to be concentrated on fewer topics, often carrying words related to the cognitive process of it insight, which characterizes chain messages. We also found that their propagation process is much more viral for both images and textual messages.