Automatic determination of the color of the Mexican semaphore of COVID-19 from the news

Detalhes bibliográficos
Autor(a) principal: Alvarez-Carmona, Miguel Ángel
Data de Publicação: 2022
Outros Autores: Aranda, Ramón
Tipo de documento: preprint
Idioma: spa
Título da fonte: SciELO Preprints
Texto Completo: https://preprints.scielo.org/index.php/scielo/preprint/view/3834
Resumo: This paper presents the analysis of textual classification models to automatically determine the Mexican regional epidemiological traffic light through COVID news. A database was collected with 4,270 news items referring to COVID, from June 1, 2020, to March 28, 2021. The label of each news item is the color of the epidemiological traffic light that the Mexican government cataloged in the week of publication of the news Classifiers such as SVM, KNN, Random Forest, and Deep Learning were applied. The results show that it is possible to take advantage of the information published in the news to determine the color of the traffic light up to 4 weeks in advance, obtaining results of up to 0.74 F-measure, which is a competitive result taking into account the imbalance of classes of this task.
id SCI-1_b20d1cb3d8b74569da430ce7ead2f9a7
oai_identifier_str oai:ops.preprints.scielo.org:preprint/3834
network_acronym_str SCI-1
network_name_str SciELO Preprints
repository_id_str
spelling Automatic determination of the color of the Mexican semaphore of COVID-19 from the newsDeterminación automática del color del semáforo Mexicano del COVID-19 a partir de las noticiasCOVID-19natural language processingtextual classificationepidemiological semaphoreCOVID-19procesamiento de lenguaje naturalclasificación textualsemáforo epidemiológicoThis paper presents the analysis of textual classification models to automatically determine the Mexican regional epidemiological traffic light through COVID news. A database was collected with 4,270 news items referring to COVID, from June 1, 2020, to March 28, 2021. The label of each news item is the color of the epidemiological traffic light that the Mexican government cataloged in the week of publication of the news Classifiers such as SVM, KNN, Random Forest, and Deep Learning were applied. The results show that it is possible to take advantage of the information published in the news to determine the color of the traffic light up to 4 weeks in advance, obtaining results of up to 0.74 F-measure, which is a competitive result taking into account the imbalance of classes of this task.Este trabajo presenta el análisis de modelos de clasificación textual para determinar automáticamente el semáforo epidemiológico regional mexicano a través de noticias de COVID. Se recolectó una base de datos con 4270 noticias referente a COVID, desde el 1 de junio de 2020 hasta el 28 de marzo de 2021. La etiqueta de cada noticia es el color del semáforo epidemiológico que el gobierno mexicano catalogó en la semana de la publicación de la noticia. Se aplicaron clasificadores como: SVM, KNN, Random Forest y Deep Learning. Los resultados muestran que es posible aprovechar la información que se publica en las noticias para determinar el color del semáforo hasta con 4 semanas de anticipación obteniendo resultados de hasta 0.74 de F-measure, el cual es un resultado competitivo tomando en cuenta el desbalance de clases de esta tarea.SciELO PreprintsSciELO PreprintsSciELO Preprints2022-03-25info:eu-repo/semantics/preprintinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://preprints.scielo.org/index.php/scielo/preprint/view/383410.1590/SciELOPreprints.3834spahttps://preprints.scielo.org/index.php/scielo/article/view/3834/7162Copyright (c) 2022 Miguel Ángel Alvarez-Carmona, Ramón Arandahttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessAlvarez-Carmona, Miguel ÁngelAranda, Ramónreponame:SciELO Preprintsinstname:SciELOinstacron:SCI2022-03-23T07:20:04Zoai:ops.preprints.scielo.org:preprint/3834Servidor de preprintshttps://preprints.scielo.org/index.php/scieloONGhttps://preprints.scielo.org/index.php/scielo/oaiscielo.submission@scielo.orgopendoar:2022-03-23T07:20:04SciELO Preprints - SciELOfalse
dc.title.none.fl_str_mv Automatic determination of the color of the Mexican semaphore of COVID-19 from the news
Determinación automática del color del semáforo Mexicano del COVID-19 a partir de las noticias
title Automatic determination of the color of the Mexican semaphore of COVID-19 from the news
spellingShingle Automatic determination of the color of the Mexican semaphore of COVID-19 from the news
Alvarez-Carmona, Miguel Ángel
COVID-19
natural language processing
textual classification
epidemiological semaphore
COVID-19
procesamiento de lenguaje natural
clasificación textual
semáforo epidemiológico
title_short Automatic determination of the color of the Mexican semaphore of COVID-19 from the news
title_full Automatic determination of the color of the Mexican semaphore of COVID-19 from the news
title_fullStr Automatic determination of the color of the Mexican semaphore of COVID-19 from the news
title_full_unstemmed Automatic determination of the color of the Mexican semaphore of COVID-19 from the news
title_sort Automatic determination of the color of the Mexican semaphore of COVID-19 from the news
author Alvarez-Carmona, Miguel Ángel
author_facet Alvarez-Carmona, Miguel Ángel
Aranda, Ramón
author_role author
author2 Aranda, Ramón
author2_role author
dc.contributor.author.fl_str_mv Alvarez-Carmona, Miguel Ángel
Aranda, Ramón
dc.subject.por.fl_str_mv COVID-19
natural language processing
textual classification
epidemiological semaphore
COVID-19
procesamiento de lenguaje natural
clasificación textual
semáforo epidemiológico
topic COVID-19
natural language processing
textual classification
epidemiological semaphore
COVID-19
procesamiento de lenguaje natural
clasificación textual
semáforo epidemiológico
description This paper presents the analysis of textual classification models to automatically determine the Mexican regional epidemiological traffic light through COVID news. A database was collected with 4,270 news items referring to COVID, from June 1, 2020, to March 28, 2021. The label of each news item is the color of the epidemiological traffic light that the Mexican government cataloged in the week of publication of the news Classifiers such as SVM, KNN, Random Forest, and Deep Learning were applied. The results show that it is possible to take advantage of the information published in the news to determine the color of the traffic light up to 4 weeks in advance, obtaining results of up to 0.74 F-measure, which is a competitive result taking into account the imbalance of classes of this task.
publishDate 2022
dc.date.none.fl_str_mv 2022-03-25
dc.type.driver.fl_str_mv info:eu-repo/semantics/preprint
info:eu-repo/semantics/publishedVersion
format preprint
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://preprints.scielo.org/index.php/scielo/preprint/view/3834
10.1590/SciELOPreprints.3834
url https://preprints.scielo.org/index.php/scielo/preprint/view/3834
identifier_str_mv 10.1590/SciELOPreprints.3834
dc.language.iso.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv https://preprints.scielo.org/index.php/scielo/article/view/3834/7162
dc.rights.driver.fl_str_mv Copyright (c) 2022 Miguel Ángel Alvarez-Carmona, Ramón Aranda
https://creativecommons.org/licenses/by/4.0
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2022 Miguel Ángel Alvarez-Carmona, Ramón Aranda
https://creativecommons.org/licenses/by/4.0
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv SciELO Preprints
SciELO Preprints
SciELO Preprints
publisher.none.fl_str_mv SciELO Preprints
SciELO Preprints
SciELO Preprints
dc.source.none.fl_str_mv reponame:SciELO Preprints
instname:SciELO
instacron:SCI
instname_str SciELO
instacron_str SCI
institution SCI
reponame_str SciELO Preprints
collection SciELO Preprints
repository.name.fl_str_mv SciELO Preprints - SciELO
repository.mail.fl_str_mv scielo.submission@scielo.org
_version_ 1797047827892797440

Registros relacionados