Um modelo de intenção de voto baseado em sistema multiagente

• Ano de defesa: 2020
• Autor(a) principal: Charcon, Douglas Yamamoto
• Orientador(a): Monteiro, Luiz Henrique Alves
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Presbiteriana Mackenzie
• Palavras-chave em Português: dinâmica de opinião; intenção de voto; rede social; sistema multiagente; sociofísica
• Área do conhecimento CNPq: CNPQ::ENGENHARIAS
• Link de acesso: https://dspace.mackenzie.br/handle/10899/28611

Personal knowledge and social relationships affect the formation and spread of different kinds of opinion in a society. In fact, the opinions of individuals are a consequence of their own convictions and of the influence exerted by their networks of real and virtual contacts. These opinions are reflected in the decision making that occurs, for example, in an election. In this work, a model of voting intention based on a multi-agent system is proposed, with the aim of predicting the result of a two-round election with three candidates running for a position in the Executive Branch. Each voter is represented by an agent, whose vote is influenced by economic, political, and social factors and the voting intention of their neighbors. Here, computer simulations are carried out in order to understand how the mentioned factors and the influence of the neighborhood determine the elected candidate. Also, the model is used to reproduce the presidential elections held in Uruguay in 2019 and in Brazil in 2010. There is a good agreement between the official results of these elections and the model results.