Account classification in online social networks with LBCA and wavelets
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.ins.2015.10.039 http://hdl.handle.net/11449/178391 |
Resumo: | We developed a wavelet-based approach for account classification that detects textual dissemination by bots on an Online Social Network (OSN). Its main objective is to match account patterns with humans, cyborgs or robots, improving the existing algorithms that automatically detect frauds. With a computational cost suitable for OSNs, the proposed approach analyses the distribution of key terms. The descriptors, a wavelet-based feature vector for each user's account, work in conjunction with a new weighting scheme, called Lexicon Based Coefficient Attenuation (LBCA) and serve as inputs to one of the classifiers tested: Random Forests and Multilayer Perceptrons. Experiments were performed using a set of posts crawled during the 2014 FIFA World Cup, obtaining accuracies within the range from 94 to 100%. |
id |
UNSP_02b9a03c8d641b89a0ea474d013f775b |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/178391 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Account classification in online social networks with LBCA and waveletsAccount classificationMultilayer perceptronsOnline social networksRandom forestsWaveletsWe developed a wavelet-based approach for account classification that detects textual dissemination by bots on an Online Social Network (OSN). Its main objective is to match account patterns with humans, cyborgs or robots, improving the existing algorithms that automatically detect frauds. With a computational cost suitable for OSNs, the proposed approach analyses the distribution of key terms. The descriptors, a wavelet-based feature vector for each user's account, work in conjunction with a new weighting scheme, called Lexicon Based Coefficient Attenuation (LBCA) and serve as inputs to one of the classifiers tested: Random Forests and Multilayer Perceptrons. Experiments were performed using a set of posts crawled during the 2014 FIFA World Cup, obtaining accuracies within the range from 94 to 100%.Londrina State University, Rod. Celso Garcia Cid km 380, Londrina-PRInstituto de Biociências Letras e Ciências Exatas Unesp - Univ Estadual Paulista (São Paulo State University), Rua Cristóvão Colombo 2265, Jd Nazareth, 15054-000, São José do Rio Preto - SPDepartament of Electrical Engineering School of Engineering at São Carlos University of São Paulo, 13566-590, São Carlos, SPInstituto de Biociências Letras e Ciências Exatas Unesp - Univ Estadual Paulista (São Paulo State University), Rua Cristóvão Colombo 2265, Jd Nazareth, 15054-000, São José do Rio Preto - SPUniversidade Estadual de Londrina (UEL)Universidade Estadual Paulista (Unesp)Universidade de São Paulo (USP)Igawa, Rodrigo AugustoBarbon Jr, SylvioPaulo, Kátia Cristina SilvaKido, Guilherme SakajiGuido, Rodrigo Capobianco [UNESP]Júnior, Mario Lemes ProençaSilva, Ivan Nunes da2018-12-11T17:30:03Z2018-12-11T17:30:03Z2016-03-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article72-83application/pdfhttp://dx.doi.org/10.1016/j.ins.2015.10.039Information Sciences, v. 332, p. 72-83.0020-0255http://hdl.handle.net/11449/17839110.1016/j.ins.2015.10.0392-s2.0-849940487442-s2.0-84994048744.pdf65420862268080670000-0002-0924-8024Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengInformation Sciences1,635info:eu-repo/semantics/openAccess2024-01-04T06:22:40Zoai:repositorio.unesp.br:11449/178391Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T22:04:45.456675Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Account classification in online social networks with LBCA and wavelets |
title |
Account classification in online social networks with LBCA and wavelets |
spellingShingle |
Account classification in online social networks with LBCA and wavelets Igawa, Rodrigo Augusto Account classification Multilayer perceptrons Online social networks Random forests Wavelets |
title_short |
Account classification in online social networks with LBCA and wavelets |
title_full |
Account classification in online social networks with LBCA and wavelets |
title_fullStr |
Account classification in online social networks with LBCA and wavelets |
title_full_unstemmed |
Account classification in online social networks with LBCA and wavelets |
title_sort |
Account classification in online social networks with LBCA and wavelets |
author |
Igawa, Rodrigo Augusto |
author_facet |
Igawa, Rodrigo Augusto Barbon Jr, Sylvio Paulo, Kátia Cristina Silva Kido, Guilherme Sakaji Guido, Rodrigo Capobianco [UNESP] Júnior, Mario Lemes Proença Silva, Ivan Nunes da |
author_role |
author |
author2 |
Barbon Jr, Sylvio Paulo, Kátia Cristina Silva Kido, Guilherme Sakaji Guido, Rodrigo Capobianco [UNESP] Júnior, Mario Lemes Proença Silva, Ivan Nunes da |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual de Londrina (UEL) Universidade Estadual Paulista (Unesp) Universidade de São Paulo (USP) |
dc.contributor.author.fl_str_mv |
Igawa, Rodrigo Augusto Barbon Jr, Sylvio Paulo, Kátia Cristina Silva Kido, Guilherme Sakaji Guido, Rodrigo Capobianco [UNESP] Júnior, Mario Lemes Proença Silva, Ivan Nunes da |
dc.subject.por.fl_str_mv |
Account classification Multilayer perceptrons Online social networks Random forests Wavelets |
topic |
Account classification Multilayer perceptrons Online social networks Random forests Wavelets |
description |
We developed a wavelet-based approach for account classification that detects textual dissemination by bots on an Online Social Network (OSN). Its main objective is to match account patterns with humans, cyborgs or robots, improving the existing algorithms that automatically detect frauds. With a computational cost suitable for OSNs, the proposed approach analyses the distribution of key terms. The descriptors, a wavelet-based feature vector for each user's account, work in conjunction with a new weighting scheme, called Lexicon Based Coefficient Attenuation (LBCA) and serve as inputs to one of the classifiers tested: Random Forests and Multilayer Perceptrons. Experiments were performed using a set of posts crawled during the 2014 FIFA World Cup, obtaining accuracies within the range from 94 to 100%. |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016-03-01 2018-12-11T17:30:03Z 2018-12-11T17:30:03Z |
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://dx.doi.org/10.1016/j.ins.2015.10.039 Information Sciences, v. 332, p. 72-83. 0020-0255 http://hdl.handle.net/11449/178391 10.1016/j.ins.2015.10.039 2-s2.0-84994048744 2-s2.0-84994048744.pdf 6542086226808067 0000-0002-0924-8024 |
url |
http://dx.doi.org/10.1016/j.ins.2015.10.039 http://hdl.handle.net/11449/178391 |
identifier_str_mv |
Information Sciences, v. 332, p. 72-83. 0020-0255 10.1016/j.ins.2015.10.039 2-s2.0-84994048744 2-s2.0-84994048744.pdf 6542086226808067 0000-0002-0924-8024 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Information Sciences 1,635 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
72-83 application/pdf |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808129390221983744 |