Cargando…

Content-based user classifier to uncover information exchange in disaster-motivated networks

Disasters strike communities around the world, with a reduced time-frame for warning and action leaving behind high rates of damage, mortality, and years in rebuilding efforts. For the past decade, social media has indicated a positive role in communicating before, during, and after disasters. One i...

Descripción completa

Detalles Bibliográficos
Autores principales: Babvey, Pouria, Gongora-Svartzman, Gabriela, Lipizzi, Carlo, Ramirez-Marquez, Jose E.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8594803/
https://www.ncbi.nlm.nih.gov/pubmed/34784364
http://dx.doi.org/10.1371/journal.pone.0259342
_version_ 1784600059316273152
author Babvey, Pouria
Gongora-Svartzman, Gabriela
Lipizzi, Carlo
Ramirez-Marquez, Jose E.
author_facet Babvey, Pouria
Gongora-Svartzman, Gabriela
Lipizzi, Carlo
Ramirez-Marquez, Jose E.
author_sort Babvey, Pouria
collection PubMed
description Disasters strike communities around the world, with a reduced time-frame for warning and action leaving behind high rates of damage, mortality, and years in rebuilding efforts. For the past decade, social media has indicated a positive role in communicating before, during, and after disasters. One important question that remained un-investigated is that whether social media efficiently connect affected individuals to disaster relief agencies, and if not, how AI models can use historical data from previous disasters to facilitate information exchange between the two groups. In this study, the BERT model is first fine-tuned using historical data and then it is used to classify the tweets associated with hurricanes Dorian and Harvey based on the type of information provided; and alongside, the network between users is constructed based on the retweets and replies on Twitter. Afterwards, some network metrics are used to measure the diffusion rate of each type of disaster-motivated information. The results show that the messages by disaster eyewitnesses get the least spread while the posts by governments and media have the highest diffusion rates through the network. Additionally, the “cautions and advice” messages get the most spread among other information types while “infrastructure and utilities” and “affected individuals” messages get the least diffusion even compared with “sympathy and support”. The analysis suggests that facilitating the propagation of information provided by affected individuals, using AI models, will be a valuable strategy to pursue in order to accelerate communication between affected individuals and survival groups during the disaster and aftermath.
format Online
Article
Text
id pubmed-8594803
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-85948032021-11-17 Content-based user classifier to uncover information exchange in disaster-motivated networks Babvey, Pouria Gongora-Svartzman, Gabriela Lipizzi, Carlo Ramirez-Marquez, Jose E. PLoS One Research Article Disasters strike communities around the world, with a reduced time-frame for warning and action leaving behind high rates of damage, mortality, and years in rebuilding efforts. For the past decade, social media has indicated a positive role in communicating before, during, and after disasters. One important question that remained un-investigated is that whether social media efficiently connect affected individuals to disaster relief agencies, and if not, how AI models can use historical data from previous disasters to facilitate information exchange between the two groups. In this study, the BERT model is first fine-tuned using historical data and then it is used to classify the tweets associated with hurricanes Dorian and Harvey based on the type of information provided; and alongside, the network between users is constructed based on the retweets and replies on Twitter. Afterwards, some network metrics are used to measure the diffusion rate of each type of disaster-motivated information. The results show that the messages by disaster eyewitnesses get the least spread while the posts by governments and media have the highest diffusion rates through the network. Additionally, the “cautions and advice” messages get the most spread among other information types while “infrastructure and utilities” and “affected individuals” messages get the least diffusion even compared with “sympathy and support”. The analysis suggests that facilitating the propagation of information provided by affected individuals, using AI models, will be a valuable strategy to pursue in order to accelerate communication between affected individuals and survival groups during the disaster and aftermath. Public Library of Science 2021-11-16 /pmc/articles/PMC8594803/ /pubmed/34784364 http://dx.doi.org/10.1371/journal.pone.0259342 Text en © 2021 Babvey et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Babvey, Pouria
Gongora-Svartzman, Gabriela
Lipizzi, Carlo
Ramirez-Marquez, Jose E.
Content-based user classifier to uncover information exchange in disaster-motivated networks
title Content-based user classifier to uncover information exchange in disaster-motivated networks
title_full Content-based user classifier to uncover information exchange in disaster-motivated networks
title_fullStr Content-based user classifier to uncover information exchange in disaster-motivated networks
title_full_unstemmed Content-based user classifier to uncover information exchange in disaster-motivated networks
title_short Content-based user classifier to uncover information exchange in disaster-motivated networks
title_sort content-based user classifier to uncover information exchange in disaster-motivated networks
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8594803/
https://www.ncbi.nlm.nih.gov/pubmed/34784364
http://dx.doi.org/10.1371/journal.pone.0259342
work_keys_str_mv AT babveypouria contentbaseduserclassifiertouncoverinformationexchangeindisastermotivatednetworks
AT gongorasvartzmangabriela contentbaseduserclassifiertouncoverinformationexchangeindisastermotivatednetworks
AT lipizzicarlo contentbaseduserclassifiertouncoverinformationexchangeindisastermotivatednetworks
AT ramirezmarquezjosee contentbaseduserclassifiertouncoverinformationexchangeindisastermotivatednetworks