Abordagem Cientométrica Orientada a Dados para Classificação Multi-Alvo dos Objetivos de Desenvolvimento Sustentável na Automação

Alexandre Dias; Gisliany Alves; Germano Lima; Ariel Alsina; Ivanovitch Silva

doi:10.20906/CBA2022/3405

Alexandre Dias Programa de Pós-Graduação em Engenharia Elétrica e de Computação, Universidade Federal do Rio Grande do Norte, RN
Gisliany Alves Programa de Pós-Graduação em Engenharia Elétrica e de Computação, Universidade Federal do Rio Grande do Norte, RN
Germano Lima Programa de Pós-Graduação em Engenharia Elétrica e de Computação, Universidade Federal do Rio Grande do Norte, RN
Ariel Alsina Departamento de Engenharia de Computação e Automação, Universidade Federal do Rio Grande do Norte, RN
Ivanovitch Silva Programa de Pós-Graduação em Engenharia Elétrica e de Computação, Universidade Federal do Rio Grande do Norte, RN; Departamento de Engenharia de Computação e Automação, Universidade Federal do Rio Grande do Norte, RN

DOI: https://doi.org/10.20906/CBA2022/3405

Keywords: Sustainable Development Goals, Scientometrics, Natural Language Processing, Recurrent Neural Networks, Multilabel Classification

Abstract

The United Nations created the 17 Sustainable Development Goals (SDGs) to promote environmental protection, economic growth, and social justice. In this scenario, science is crucial to solving the challenges addressed by the SDGs. SciVal, for example, is a tool that tracks scientific publications related to the SDGs with the support of a team of experts. Aiming to reduce the need for specialized knowledge and to provide a more autonomous tool, this study proposes a multi-label classification model based on natural language processing and recurrent neural networks to map scientific publications to the SDGs. The proposed model is tested with the articles of the Brazilian Congress of Automatics (CBA) 2020. The data used to train the model comprises manuscript titles acquired from the Scopus database using the SciVal analytics tool, and they are related to 16 out of the 17 SDGs. Results have shown that the papers published in the CBA 2020 focused on SDGs 7, and 9, which are related to clean energy and industry innovation. Furthermore, all SDGs were associated with at least one publication, indicating that intelligent automation can contribute in a interdisciplinary way to the SDGs implementation.