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

dc.contributor.authorVasquez, Rodrigo
dc.contributor.authorRiquelme, Fabián
dc.contributor.authorGonzalez-Cantergiani, Pablo
dc.contributor.authorVasquez, Cristobal
dc.date.accessioned2022-11-30T02:47:05Z
dc.date.available2022-11-30T02:47:05Z
dc.date.issued2021
dc.description.abstractOnline 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.en_ES
dc.facultadFacultad de Ingenieríaen_ES
dc.file.nameVasquez_Usi2021.pdf
dc.identifier.citationVASQUEZ, Rodrigo; RIQUELME, Fabián; GONZALEZ-CANTERGIANI, Pablo y VASQUEZ, Cristobal. Using centrality measures to improve the classification performance of tweets during natural disasters. Ingeniare. Rev. chil. ing. [online]. 2021, vol.29, n.1 [citado 2022-11-23], pp.73-86. Disponible en: <http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0718-33052021000100073&lng=es&nrm=iso>. ISSN 0718-3305. http://dx.doi.org/10.4067/S0718-33052021000100073.en_ES
dc.identifier.doihttp://dx.doi.org/10.4067/S0718-
dc.identifier.urihttp://repositoriobibliotecas.uv.cl/handle/uvscl/7568
dc.languageen
dc.publisherUniversidad De Tarapacá
dc.sourceIngeniare. Revista chilena de ingeniería
dc.subjectACTIVE LEARNINGen_ES
dc.subjectTWITTERen_ES
dc.subjectCENTRALITY MEASUREen_ES
dc.subjectDISASTER RESPONSEen_ES
dc.subjectUSER INFLUENCEen_ES
dc.titleUsing centrality measures to improve the classification performance of tweets during natural disasters
dc.typeArticulo
uv.departamentoEscuela de Ingenieria Informatica

Archivos

Bloque original
Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
Vasquez_Usi2021.pdf
Tamaño:
994.75 KB
Formato:
Adobe Portable Document Format
Descripción: