Text classification: an approach using machine learning

• Autor(a) principal: Cardoso, Fábio Eder
• Data de Publicação: 2023
• Outros Autores: Ferneda, Edberto, Botega, Leonardo
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Revista EDICIC
• DOI: 10.62758/re.v3i3.212
• Texto Completo: https://ojs.edicic.org/revistaedicic/article/view/212
• topic: Classificação; Machine Learning; Algoritmos; Informação; Ciência da Informação; Clasificación; Machine Learning; Algoritmos; Información; Ciencias de la Información; Classification; Machine Learning; Algorithms; Information; Information Science

Text classification has been employed as a foundation for organizing knowledge across a wide range of fields, as it allows for the grouping of categories to guide the segmentation of these domains. In the digital information age, where there is an abundance of data spread across cloud computing environments, the use of informational technologies is essential to facilitate the classification process of this data. Within this framework, Information Science plays a pivotal role in the production, organization, transmission, and utilization of information across diverse fields, including computer science, mathematics, artificial intelligence, among others. Through technology, when information is appropriately classified, it can be made available to society more effectively. The primary aim of this article is to address contexts regarding text classification using Machine Learning. This research is exploratory, adopting an experimental method, and employs a quantitative approach as its data analysis technique. As a result, after utilizing the Euclidean distance algorithm, a distance matrix and hierarchical grouping were established, along with a word cloud, highlighting terms of significance from the documents.