TCC - Bacharelado em Ciência da Computação (Sede)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/415
Navegar
Item Analisando a presença feminina no Ensino Superior em Tecnologia no Brasil ao longo dos anos de 2013 a 2022(2024-03-07) Ramos, Giuliane Benjamim de Oliveira; Alencar, Andrêza Leite de; Furtado, Ana Paula Carvalho Cavalcanti; http://lattes.cnpq.br/5862330768739698; http://lattes.cnpq.br/6060587704569605; http://lattes.cnpq.br/6421196285147828Masculine stigma, low family encouragement, and lack of representation are the main factors that justify the underrepresentation of women in the technology field. Therefore, this paper aims to highlight the current female landscape in Information Technology (IT) higher education courses in Brazil. To achieve this purpose, a literature review and analysis of microdata from the Higher Education Census from 2013 to 2022, provided by the National Institute for Educational Studies and Research An´ısio Teixeira (INEP), were conducted. The analysis shows significantly low female representation in higher education technology courses over the analyzed period - female enrollments do not exceed 17%, the completion rate averages 15%, and the Southeast region has the highest number of female representatives in IT courses, with São Paulo standing out. However, a trend of increase can be observed in the last two years.Item Sistema de suporte à criação de modelos de classificação para a previsão de evasão no ensino superior(2024-03-08) Costa, Tarcísio Barbosa da; Alencar, Andrêza Leite de; Albuquerque Júnior, Gabriel Alves de; http://lattes.cnpq.br/1399502815770584; http://lattes.cnpq.br/6060587704569605; http://lattes.cnpq.br/6560255346406064Student dropout is one of the greatest challenges faced by university degree institutions. In order to mitigate it, those institutions develop moitoring and analysis tools regarding this phenomenon. One of many existing methodologies to do so is the recognition of student characteristics that leads to dropout, and ond of many existing tools is SABIA: a virtual dashboard responsible for supporting evidence-based management allied to concepts like Learning/Academic Analytics and Business Intelligence. This work expands SABIA through a new page able to create user-customizable supervisioned learning models, offering feature analysis from students and predicting their final status based on those features. Information obtained through those models enables the recognition of risk features on student profiles and assists managers on providin guidelines for applying countermeasures against dropout.