A influência do design informativo e a visualização de dados aplicados à experiência do usuário em sistemas de recomendação de plataformas de streaming

• Autor(a) principal: Calisto, Allan de Aguiar
• Data de Publicação: 2023
• Outros Autores: Nogueira, Gabriel Veras, Messias, João Victor Alves, Cabral, Leonardo Matos
• Tipo de documento: Trabalho de conclusão de curso
• Idioma: por
• Título da fonte: Biblioteca Digital de Teses e Dissertações da PUC_SP
• Texto Completo: https://repositorio.pucsp.br/jspui/handle/handle/40313; https://www.figma.com/file/5LVEYpJTHQ56d5T5GOiOaO/TCC---Netflix?type=design&node-id=0%3A1&mode=design&t=7HxLgCS4EXkmEj9X-1
• topic: CNPQ::CIENCIAS SOCIAIS APLICADAS::DESENHO INDUSTRIAL::DESENHO DE PRODUTO; Visualização de dados; Sistemas de recomendação; Usabilidade; Streaming; Data visualization; Recommendation systems; Usability; Streaming

The work takes an approach to recommendation systems, which, over the years, have been responsible for suggesting relevant, personalized, and attractive content to each user based on their respective usage history and preferences. Therefore, the implementation of an efficient recommendation system is based on machine learning, an area of artificial intelligence, which plays a crucial role in the user experience and the success of these platforms involved. For the purpose of recommendation, such algorithms prove to be an essential tool for the business of companies such as e-commerce (Amazon) and streaming services (Netflix and Disney+), contributing to good audience retention. To this end, it is worth highlighting the alarming disregard for the effectiveness of communicating factors linked to data collection and privacy, given that such systems are assiduously accurate in terms of profile analysis, highlighting the ideal preferences and interests of each consumer. Given this, the question arises of how such visibility and information methods influence the usability and user experience in online streaming services applied to digital interface recommendation systems. In this sense, demotivation and frustration are common sensations among users concerned about the critical vulnerability of personal data that circulates freely between current algorithms. Another aspect that transparency in the use of data linked to recommendation systems can act on is the influence and interaction between the user and the platform, which can contribute to a good experience, if carried out correctly, using cognitive psychological biases linked to design. There are even results that demonstrate, like Spotify, that through the clarity of the reported data, the relationship between user and platform improves based on the acceptance of what is presented through similarity filtering. Allowing the creation of assertive individual user profiles, in addition to respecting their privacy rights.