Processo de ETL para inserção de dados estatísticos do INEP com foco em mulheres nos cursos de áreas STEM no grafo de conhecimento da plataforma ELLAS

Abstract

The discussion about why it is important to talk about gender in STEM can be limited given the lack of data highlighting this issue in Latin America. Therefore, this work is part of the ELLAS research network, which aims to develop an Open Data platform in Latin America to encourage the development of gender equality policies with a focus on leadership in STEM. To advance in this direction, this research aims to propose an automated process via ETL for the triplification of statistical data from INEP focusing on women in higher education in STEM areas, in order to integrate the data into the knowledge graph of the ELLAS platform and facilitate the reuse of this data. This required extending the pre-existing model and enriching it semantically, aspects also considered in this research. As a result, integration was achieved using the pipeline developed, making it possible to answer questions about women in the context of Higher Education on STEM using the knowledge graph.