A Google trends spatial clustering approach for a worldwide Twitter user geolocation
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/1822/66815 |
Resumo: | User location data is valuable for diverse social media analytics. In this paper, we address the non-trivial task of estimating a worldwide city-level Twitter user location considering only historical tweets. We propose a purely unsupervised approach that is based on a synthetic geographic sampling of Google Trends (GT) city-level frequencies of tweet nouns and three clustering algorithms. The approach was validated empirically by using a recently collected dataset, with 3,268 worldwide city-level locations of Twitter users, obtaining competitive results when compared with a state-of-the-art Word Distribution (WD) user location estimation method. The best overall results were achieved by the GT noun DBSCAN (GTN-DB) method, which is computationally fast, and correctly predicts the ground truth locations of 15%, 23%, 39% and 58% of the users for tolerance distances of 250 km, 500 km, 1,000 km and 2,000 km. |
id |
RCAP_df95b87eebbb7f15bc837af2eb6619a9 |
---|---|
oai_identifier_str |
oai:repositorium.sdum.uminho.pt:1822/66815 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
A Google trends spatial clustering approach for a worldwide Twitter user geolocationCity-level geolocationClusteringGoogle TrendsNatural language processingTwitterEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e InformáticaScience & TechnologyUser location data is valuable for diverse social media analytics. In this paper, we address the non-trivial task of estimating a worldwide city-level Twitter user location considering only historical tweets. We propose a purely unsupervised approach that is based on a synthetic geographic sampling of Google Trends (GT) city-level frequencies of tweet nouns and three clustering algorithms. The approach was validated empirically by using a recently collected dataset, with 3,268 worldwide city-level locations of Twitter users, obtaining competitive results when compared with a state-of-the-art Word Distribution (WD) user location estimation method. The best overall results were achieved by the GT noun DBSCAN (GTN-DB) method, which is computationally fast, and correctly predicts the ground truth locations of 15%, 23%, 39% and 58% of the users for tolerance distances of 250 km, 500 km, 1,000 km and 2,000 km.The work of P. Cortez was supported by FCT – Funda ̧c ̃ao para a Ciˆencia eTecnologia within the R&D Units Project Scope: UIDB/00319/2020. We wouldalso like to thank the anonymous reviewers for their helpful suggestions.ElsevierUniversidade do MinhoZola, PaolaRagno, CostantinoCortez, Paulo20202020-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/1822/66815eng0306-457310.1016/j.ipm.2020.102312https://www.sciencedirect.com/science/article/pii/S0306457320308074info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-21T12:48:52Zoai:repositorium.sdum.uminho.pt:1822/66815Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T19:47:13.048461Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
A Google trends spatial clustering approach for a worldwide Twitter user geolocation |
title |
A Google trends spatial clustering approach for a worldwide Twitter user geolocation |
spellingShingle |
A Google trends spatial clustering approach for a worldwide Twitter user geolocation Zola, Paola City-level geolocation Clustering Google Trends Natural language processing Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática Science & Technology |
title_short |
A Google trends spatial clustering approach for a worldwide Twitter user geolocation |
title_full |
A Google trends spatial clustering approach for a worldwide Twitter user geolocation |
title_fullStr |
A Google trends spatial clustering approach for a worldwide Twitter user geolocation |
title_full_unstemmed |
A Google trends spatial clustering approach for a worldwide Twitter user geolocation |
title_sort |
A Google trends spatial clustering approach for a worldwide Twitter user geolocation |
author |
Zola, Paola |
author_facet |
Zola, Paola Ragno, Costantino Cortez, Paulo |
author_role |
author |
author2 |
Ragno, Costantino Cortez, Paulo |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade do Minho |
dc.contributor.author.fl_str_mv |
Zola, Paola Ragno, Costantino Cortez, Paulo |
dc.subject.por.fl_str_mv |
City-level geolocation Clustering Google Trends Natural language processing Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática Science & Technology |
topic |
City-level geolocation Clustering Google Trends Natural language processing Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática Science & Technology |
description |
User location data is valuable for diverse social media analytics. In this paper, we address the non-trivial task of estimating a worldwide city-level Twitter user location considering only historical tweets. We propose a purely unsupervised approach that is based on a synthetic geographic sampling of Google Trends (GT) city-level frequencies of tweet nouns and three clustering algorithms. The approach was validated empirically by using a recently collected dataset, with 3,268 worldwide city-level locations of Twitter users, obtaining competitive results when compared with a state-of-the-art Word Distribution (WD) user location estimation method. The best overall results were achieved by the GT noun DBSCAN (GTN-DB) method, which is computationally fast, and correctly predicts the ground truth locations of 15%, 23%, 39% and 58% of the users for tolerance distances of 250 km, 500 km, 1,000 km and 2,000 km. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020 2020-01-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/1822/66815 |
url |
http://hdl.handle.net/1822/66815 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
0306-4573 10.1016/j.ipm.2020.102312 https://www.sciencedirect.com/science/article/pii/S0306457320308074 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133044614889472 |