Classification of news categories using BERT

• Autores: Machado Medina, Bradlhy Luis, Santillana Quirita, César Alonso, Bautista Luque, Sharmelyn Violeta
• Formato: artículo
• Fecha de Publicación: 2023
• Institución: Universidad La Salle
• Repositorio: Revistas - Universidad La Salle
• Lenguaje: español
• OAI Identifier: oai:ojs.revistas.ulasalle.edu.pe:article/98
• Enlace del recurso: https://revistas.ulasalle.edu.pe/innosoft/article/view/98; https://doi.org/10.48168/innosoft.s12.a98; https://purl.org/42411/s12/a98; https://n2t.net/ark:/42411/s12/a98
• Nivel de acceso: acceso abierto
• Materia: News classification; natural language processing; BERT; machine learning; artificial intelligence; clasificacion de noticias; procesamiento de lenguaje natural; inteligencia artificial

The present project consists of developing a Natural Language Processing model to classify news using a set of data or DataSets already evaluated. The main objective is to create a system that can automatically identify and assign news to one of the predefined categories: business, entertainment, politics, sports or technology. This involves data preprocessing, feature extraction, training a machinelearning model and then evaluating its performance using metrics such as "accuracy", "recall 2" F1 - score". This will allow to determine how well the model can predict the correct category for a new or unlabeled news item. If the performance of the model is satisfactory, it can be used to classify unlabeled news in real time. In summary, it seeks to provide an efficient and accurate solution for organizing and labeling the informative content of a news item with the help of Artificial Intelligence.