Using centrality measures to improve the classification performance of tweets during natural disasters

ABSTRACT Online social networks like Twitter facilitate instant communication during natural disasters. A key problem is to distinguish in real-time the most assertive and contingent tweets related to the current disaster from the whole streaming. To address this problem, machine learning allows to...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Vásquez,Rodrigo, Riquelme,Fabián, González-Cantergiani,Pablo, Vásquez,Cristobal
Lenguaje:English
Publicado: Universidad de Tarapacá. 2021
Materias:
Acceso en línea:http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-33052021000100073
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:scielo:S0718-33052021000100073
record_format dspace
spelling oai:scielo:S0718-330520210001000732021-04-15Using centrality measures to improve the classification performance of tweets during natural disastersVásquez,RodrigoRiquelme,FabiánGonzález-Cantergiani,PabloVásquez,Cristobal Active learning Twitter centrality measure disaster response user influence ABSTRACT Online social networks like Twitter facilitate instant communication during natural disasters. A key problem is to distinguish in real-time the most assertive and contingent tweets related to the current disaster from the whole streaming. To address this problem, machine learning allows to classify tweets according to their relevance or credibility. In this article, it is proposed to use centrality measures to improve the training data sample of active learning classifiers. As a case study, tweets collected during the massive floods in Santiago of Chile at 2016 are considered. This approach improves the consistency and pertinence of the labeling process, as well as the classifiers' performance.info:eu-repo/semantics/openAccessUniversidad de Tarapacá.Ingeniare. Revista chilena de ingeniería v.29 n.1 20212021-03-01text/htmlhttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-33052021000100073en10.4067/S0718-33052021000100073
institution Scielo Chile
collection Scielo Chile
language English
topic Active learning
Twitter
centrality measure
disaster response
user influence
spellingShingle Active learning
Twitter
centrality measure
disaster response
user influence
Vásquez,Rodrigo
Riquelme,Fabián
González-Cantergiani,Pablo
Vásquez,Cristobal
Using centrality measures to improve the classification performance of tweets during natural disasters
description ABSTRACT Online social networks like Twitter facilitate instant communication during natural disasters. A key problem is to distinguish in real-time the most assertive and contingent tweets related to the current disaster from the whole streaming. To address this problem, machine learning allows to classify tweets according to their relevance or credibility. In this article, it is proposed to use centrality measures to improve the training data sample of active learning classifiers. As a case study, tweets collected during the massive floods in Santiago of Chile at 2016 are considered. This approach improves the consistency and pertinence of the labeling process, as well as the classifiers' performance.
author Vásquez,Rodrigo
Riquelme,Fabián
González-Cantergiani,Pablo
Vásquez,Cristobal
author_facet Vásquez,Rodrigo
Riquelme,Fabián
González-Cantergiani,Pablo
Vásquez,Cristobal
author_sort Vásquez,Rodrigo
title Using centrality measures to improve the classification performance of tweets during natural disasters
title_short Using centrality measures to improve the classification performance of tweets during natural disasters
title_full Using centrality measures to improve the classification performance of tweets during natural disasters
title_fullStr Using centrality measures to improve the classification performance of tweets during natural disasters
title_full_unstemmed Using centrality measures to improve the classification performance of tweets during natural disasters
title_sort using centrality measures to improve the classification performance of tweets during natural disasters
publisher Universidad de Tarapacá.
publishDate 2021
url http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-33052021000100073
work_keys_str_mv AT vasquezrodrigo usingcentralitymeasurestoimprovetheclassificationperformanceoftweetsduringnaturaldisasters
AT riquelmefabian usingcentralitymeasurestoimprovetheclassificationperformanceoftweetsduringnaturaldisasters
AT gonzalezcantergianipablo usingcentralitymeasurestoimprovetheclassificationperformanceoftweetsduringnaturaldisasters
AT vasquezcristobal usingcentralitymeasurestoimprovetheclassificationperformanceoftweetsduringnaturaldisasters
_version_ 1714203487876677632