Caracterização de usuários no Instagram

Detalhes bibliográficos
Ano de defesa: 2021
Autor(a) principal: Oliveira, Rodrigo Ribeiro lattes
Orientador(a): Rocha Junior, João Batista da lattes
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Universidade Estadual de Feira de Santana
Programa de Pós-Graduação: Programa de Pós-Graduação em Ciência da Computação
Departamento: DEPARTAMENTO DE TECNOLOGIA
País: Brasil
Palavras-chave em Português:
Palavras-chave em Inglês:
Área do conhecimento CNPq:
Link de acesso: http://tede2.uefs.br:8080/handle/tede/1507
Resumo: With the popularization of social media, more and more data is created, generating new opportunities of extracting knowledge from it. An example of social media that became popular in recent years is Instagram, whose focus is image sharing. For marketing purposes, the characterization of users is a very important task, because it allows to deliver specific advertisements for each group of users. This approach allows for applications in marketing, pointing to users within an intended demography. This problem is tackled in this work, in particular, the determination of age range and professional area in Instagram users that are native speakers of Portuguese. Two datasets of Instagram profiles were built, one labeled with the age range and another with the professional area of the users. The classifiers Random Forest and Support Vector Machines were used for determining these characteristics, through textual and behavioral attributes. The best results achieved have a accuracy of 60\%, performance superior to the baseline for each problem.