Publicação

Dynamic topic modeling using social network analytics

Ver documento

Detalhes bibliográficos
Resumo:Topic modeling or inference has been one of the well-known problems in the area of text mining. It deals with the automatic categorisation of words or documents into similarity groups also known as topics. In most of the social media platforms such as Twitter, Instagram, and Facebook, hashtags are used to define the content of posts. Therefore, modelling of hashtags helps in categorising posts as well as analysing user preferences. In this work, we tried to address this problem involving hashtags that stream in real-time. Our approach encompasses graph of hashtags, dynamic sampling and modularity based community detection over the data from a popular social media engagement application. Further, we analysed the topic clusters’ structure and quality using empirical experiments. The results unveil latent semantic relations between hashtags and also show frequent hashtags in a cluster. Moreover, in this approach, the words in different languages are treated synonymously. Besides, we also observed top trending topics and correlated clusters.
Autores principais:Tabassum, Shazia
Outros Autores:Gama, João; Azevedo, Paulo J.; Teixeira, Luis; Martins, Carlos; Martins, Andre
Assunto:Ciências Naturais::Ciências da Computação e da Informação Indústria, inovação e infraestruturas
Ano:2021
País:Portugal
Tipo de documento:comunicação em conferência
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
_version_ 1867439075457236992
author Tabassum, Shazia
author2 Gama, João
Azevedo, Paulo J.
Teixeira, Luis
Martins, Carlos
Martins, Andre
author2_role author
author
author
author
author
author_facet Tabassum, Shazia
Gama, João
Azevedo, Paulo J.
Teixeira, Luis
Martins, Carlos
Martins, Andre
author_role author
contributor_name_str_mv RepositóriUM - Universidade do Minho
country_str PT
creators_json_txt [{\"Person.name\":\"Tabassum, Shazia\"},{\"Person.name\":\"Gama, João\"},{\"Person.name\":\"Azevedo, Paulo J.\"},{\"Person.name\":\"Teixeira, Luis\"},{\"Person.name\":\"Martins, Carlos\"},{\"Person.name\":\"Martins, Andre\"}]
datacite.contributors.contributor.contributorName.fl_str_mv RepositóriUM - Universidade do Minho
datacite.creators.creator.creatorName.fl_str_mv Tabassum, Shazia
Gama, João
Azevedo, Paulo J.
Teixeira, Luis
Martins, Carlos
Martins, Andre
datacite.date.Accepted.fl_str_mv 2021-09-01T00:00:00Z
datacite.date.available.fl_str_mv 2024-03-31T12:32:17Z
datacite.date.embargoed.fl_str_mv 2024-03-31T12:32:17Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Ciências Naturais::Ciências da Computação e da Informação
Indústria, inovação e infraestruturas
datacite.titles.title.fl_str_mv Dynamic topic modeling using social network analytics
dc.contributor.none.fl_str_mv RepositóriUM - Universidade do Minho
dc.creator.none.fl_str_mv Tabassum, Shazia
Gama, João
Azevedo, Paulo J.
Teixeira, Luis
Martins, Carlos
Martins, Andre
dc.date.Accepted.fl_str_mv 2021-09-01T00:00:00Z
dc.date.available.fl_str_mv 2024-03-31T12:32:17Z
dc.date.embargoed.fl_str_mv 2024-03-31T12:32:17Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/1822/90304
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Springer, Cham
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.rights.rights.copyright.fl_str_mv openAccess
dc.subject.none.fl_str_mv Ciências Naturais::Ciências da Computação e da Informação
Indústria, inovação e infraestruturas
dc.title.fl_str_mv Dynamic topic modeling using social network analytics
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_5794
description Topic modeling or inference has been one of the well-known problems in the area of text mining. It deals with the automatic categorisation of words or documents into similarity groups also known as topics. In most of the social media platforms such as Twitter, Instagram, and Facebook, hashtags are used to define the content of posts. Therefore, modelling of hashtags helps in categorising posts as well as analysing user preferences. In this work, we tried to address this problem involving hashtags that stream in real-time. Our approach encompasses graph of hashtags, dynamic sampling and modularity based community detection over the data from a popular social media engagement application. Further, we analysed the topic clusters’ structure and quality using empirical experiments. The results unveil latent semantic relations between hashtags and also show frequent hashtags in a cluster. Moreover, in this approach, the words in different languages are treated synonymously. Besides, we also observed top trending topics and correlated clusters.
dirty 0
eu_rights_str_mv openAccess
format conferencePaper
fulltext.url.fl_str_mv https://repositorium.uminho.pt/bitstreams/444e3394-ae89-41ca-8406-ec46e38cb987/download
id rum_d0349724173ab8eb151fb7ab2de6cbd2
identifier.url.fl_str_mv https://hdl.handle.net/1822/90304
instacron_str repositorium
institution Universidade do Minho
instname_str Universidade do Minho
language eng
network_acronym_str rum
network_name_str RepositóriUM - Universidade do Minho
oai_identifier_str oai:repositorium.uminho.pt:1822/90304
organization_str_mv urn:organizationAcronym:repositorium
person_str_mv Tabassum, Shazia
Gama, João
Azevedo, Paulo J.
Teixeira, Luis
Martins, Carlos
Martins, Andre
publishDate 2021
publisher.none.fl_str_mv Springer, Cham
reponame_str RepositóriUM - Universidade do Minho
repository_id_str urn:repositoryAcronym:rum
service_str_mv urn:repositoryAcronym:rum
spelling engSpringer, ChamporTopic modeling or inference has been one of the well-known problems in the area of text mining. It deals with the automatic categorisation of words or documents into similarity groups also known as topics. In most of the social media platforms such as Twitter, Instagram, and Facebook, hashtags are used to define the content of posts. Therefore, modelling of hashtags helps in categorising posts as well as analysing user preferences. In this work, we tried to address this problem involving hashtags that stream in real-time. Our approach encompasses graph of hashtags, dynamic sampling and modularity based community detection over the data from a popular social media engagement application. Further, we analysed the topic clusters’ structure and quality using empirical experiments. The results unveil latent semantic relations between hashtags and also show frequent hashtags in a cluster. Moreover, in this approach, the words in different languages are treated synonymously. Besides, we also observed top trending topics and correlated clusters.application/pdfporDynamic topic modeling using social network analyticsTabassum, ShaziaGama, JoãoAzevedo, Paulo J.Teixeira, LuisMartins, CarlosMartins, AndreHostingInstitutionOrganizationalRepositóriUM - Universidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.ptCITATIONTabassum, S., Gama, J., Azevedo, P., Teixeira, L., Martins, C., Martins, A. (2021). Dynamic Topic Modeling Using Social Network Analytics. In: Marreiros, G., Melo, F.S., Lau, N., Lopes Cardoso, H., Reis, L.P. (eds) Progress in Artificial Intelligence. EPIA 2021. Lecture Notes in Computer Science(), vol 12981. Springer, Cham. https://doi.org/10.1007/978-3-030-86230-5_39ISBNIsPartOf978-3-030-86229-9DOIIsPartOf10.1007/978-3-030-86230-5_39EISBNIsPartOf978-3-030-86230-52024-03-31T12:32:17Z2021-092021-09-01T00:00:00ZHandlehttps://hdl.handle.net/1822/90304http://purl.org/coar/access_right/c_abf2open accesshttp://www.oecd.org/science/inno/38235147.pdfFields of Science and Technology (FOS)Ciências Naturais::Ciências da Computação e da Informaçãohttps://sdgs.un.org/goalsSustainable Development Goals (SDG)Indústria, inovação e infraestruturas1417502 bytesother research producthttp://purl.org/coar/resource_type/c_5794conference paper2021-09http://creativecommons.org/licenses/by-nc-sa/4.0/openAccesshttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorium.uminho.pt/bitstreams/444e3394-ae89-41ca-8406-ec46e38cb987/download
spellingShingle Dynamic topic modeling using social network analytics
Tabassum, Shazia
Ciências Naturais::Ciências da Computação e da Informação
Indústria, inovação e infraestruturas
status SINGLETON
subject.other.fl_str_mv Ciências Naturais::Ciências da Computação e da Informação
Indústria, inovação e infraestruturas
title Dynamic topic modeling using social network analytics
title_full Dynamic topic modeling using social network analytics
title_fullStr Dynamic topic modeling using social network analytics
title_full_unstemmed Dynamic topic modeling using social network analytics
title_short Dynamic topic modeling using social network analytics
title_sort Dynamic topic modeling using social network analytics
topic Ciências Naturais::Ciências da Computação e da Informação
Indústria, inovação e infraestruturas
topic_facet Ciências Naturais::Ciências da Computação e da Informação
Indústria, inovação e infraestruturas
url https://hdl.handle.net/1822/90304
visible 1