Computational fact checking from knowledge networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2015 |
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/10400.7/393 |
Resumo: | Traditional fact checking by expert journalists cannot keep up with the enormous volume of information that is now generated online. Computational fact checking may significantly enhance our ability to evaluate the veracity of dubious information. Here we show that the complexities of human fact checking can be approximated quite well by finding the shortest path between concept nodes under properly defined semantic proximity metrics on knowledge graphs. Framed as a network problem this approach is feasible with efficient computational techniques. We evaluate this approach by examining tens of thousands of claims related to history, entertainment, geography, and biographical information using a public knowledge graph extracted from Wikipedia. Statements independently known to be true consistently receive higher support via our method than do false ones. These findings represent a significant step toward scalable computational fact-checking methods that may one day mitigate the spread of harmful misinformation. |
id |
RCAP_9a05afae1d864787bbea07c972a9bb1a |
---|---|
oai_identifier_str |
oai:arca.igc.gulbenkian.pt:10400.7/393 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Computational fact checking from knowledge networksComputer Science - Computers and Societycs.SIPhysics - Physics and SocietyTraditional fact checking by expert journalists cannot keep up with the enormous volume of information that is now generated online. Computational fact checking may significantly enhance our ability to evaluate the veracity of dubious information. Here we show that the complexities of human fact checking can be approximated quite well by finding the shortest path between concept nodes under properly defined semantic proximity metrics on knowledge graphs. Framed as a network problem this approach is feasible with efficient computational techniques. We evaluate this approach by examining tens of thousands of claims related to history, entertainment, geography, and biographical information using a public knowledge graph extracted from Wikipedia. Statements independently known to be true consistently receive higher support via our method than do false ones. These findings represent a significant step toward scalable computational fact-checking methods that may one day mitigate the spread of harmful misinformation.Swiss National Science Foundation fellowship: (142353), Lilly Endowment, the James S. McDonnell Foundation, National Science Foundation grant: (CCF-1101743), Department of Defense grant: (W911NF-12-1-0037).PLOSARCAGiovanni Luca CiampagliaPrashant ShiralkarLuis M. RochaJohan BollenFilippo MenczerAlessandro Flammini2015-10-13T11:48:12Z2015-06-172015-06-17T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.7/393engCiampaglia GL, Shiralkar P, Rocha LM, Bollen J, Menczer F, Flammini A (2015) Computational Fact Checking from Knowledge Networks. PLoS ONE 10(6): e0128193. doi:10.1371/ journal.pone.012819310.1371/journal.pone.0128193info: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:RCAAP2022-11-29T14:34:47Zoai:arca.igc.gulbenkian.pt:10400.7/393Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T16:11:41.552310Repositório 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 |
Computational fact checking from knowledge networks |
title |
Computational fact checking from knowledge networks |
spellingShingle |
Computational fact checking from knowledge networks Giovanni Luca Ciampaglia Computer Science - Computers and Society cs.SI Physics - Physics and Society |
title_short |
Computational fact checking from knowledge networks |
title_full |
Computational fact checking from knowledge networks |
title_fullStr |
Computational fact checking from knowledge networks |
title_full_unstemmed |
Computational fact checking from knowledge networks |
title_sort |
Computational fact checking from knowledge networks |
author |
Giovanni Luca Ciampaglia |
author_facet |
Giovanni Luca Ciampaglia Prashant Shiralkar Luis M. Rocha Johan Bollen Filippo Menczer Alessandro Flammini |
author_role |
author |
author2 |
Prashant Shiralkar Luis M. Rocha Johan Bollen Filippo Menczer Alessandro Flammini |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
ARCA |
dc.contributor.author.fl_str_mv |
Giovanni Luca Ciampaglia Prashant Shiralkar Luis M. Rocha Johan Bollen Filippo Menczer Alessandro Flammini |
dc.subject.por.fl_str_mv |
Computer Science - Computers and Society cs.SI Physics - Physics and Society |
topic |
Computer Science - Computers and Society cs.SI Physics - Physics and Society |
description |
Traditional fact checking by expert journalists cannot keep up with the enormous volume of information that is now generated online. Computational fact checking may significantly enhance our ability to evaluate the veracity of dubious information. Here we show that the complexities of human fact checking can be approximated quite well by finding the shortest path between concept nodes under properly defined semantic proximity metrics on knowledge graphs. Framed as a network problem this approach is feasible with efficient computational techniques. We evaluate this approach by examining tens of thousands of claims related to history, entertainment, geography, and biographical information using a public knowledge graph extracted from Wikipedia. Statements independently known to be true consistently receive higher support via our method than do false ones. These findings represent a significant step toward scalable computational fact-checking methods that may one day mitigate the spread of harmful misinformation. |
publishDate |
2015 |
dc.date.none.fl_str_mv |
2015-10-13T11:48:12Z 2015-06-17 2015-06-17T00:00:00Z |
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/10400.7/393 |
url |
http://hdl.handle.net/10400.7/393 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Ciampaglia GL, Shiralkar P, Rocha LM, Bollen J, Menczer F, Flammini A (2015) Computational Fact Checking from Knowledge Networks. PLoS ONE 10(6): e0128193. doi:10.1371/ journal.pone.0128193 10.1371/journal.pone.0128193 |
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 |
PLOS |
publisher.none.fl_str_mv |
PLOS |
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_ |
1799130572229967872 |