Twitter: a good place to detect health conditions.
Identifieur interne : 000202 ( Main/Exploration ); précédent : 000201; suivant : 000203Twitter: a good place to detect health conditions.
Auteurs : Víctor M. Prieto [Espagne] ; Sérgio Matos [Portugal] ; Manuel Álvarez [Espagne] ; Fidel Cacheda [Espagne] ; José Luís Oliveira [Portugal]Source :
- PloS one [ 1932-6203 ] ; 2014.
Descripteurs français
- KwdFr :
- Connaissances, attitudes et pratiques en santé (MeSH), Courbe ROC (MeSH), Création de blogues (statistiques et données numériques), Dépression (épidémiologie), Espagne (épidémiologie), Femelle (MeSH), Grippe humaine (épidémiologie), Grossesse (MeSH), Humains (MeSH), Intelligence artificielle (statistiques et données numériques), Portugal (épidémiologie), Troubles de l'alimentation (épidémiologie).
- MESH :
- statistiques et données numériques : Création de blogues, Intelligence artificielle.
- épidémiologie : Dépression, Espagne, Grippe humaine, Portugal, Troubles de l'alimentation.
- Connaissances, attitudes et pratiques en santé, Courbe ROC, Femelle, Grossesse, Humains.
English descriptors
- KwdEn :
- Artificial Intelligence (statistics & numerical data), Blogging (statistics & numerical data), Depression (epidemiology), Feeding and Eating Disorders (epidemiology), Female (MeSH), Health Knowledge, Attitudes, Practice (MeSH), Humans (MeSH), Influenza, Human (epidemiology), Portugal (epidemiology), Pregnancy (MeSH), ROC Curve (MeSH), Spain (epidemiology).
- MESH :
- epidemiology : Depression, Feeding and Eating Disorders, Influenza, Human, Portugal, Spain.
- statistics & numerical data : Artificial Intelligence, Blogging.
- Female, Health Knowledge, Attitudes, Practice, Humans, Pregnancy, ROC Curve.
Abstract
With the proliferation of social networks and blogs, the Internet is increasingly being used to disseminate personal health information rather than just as a source of information. In this paper we exploit the wealth of user-generated data, available through the micro-blogging service Twitter, to estimate and track the incidence of health conditions in society. The method is based on two stages: we start by extracting possibly relevant tweets using a set of specially crafted regular expressions, and then classify these initial messages using machine learning methods. Furthermore, we selected relevant features to improve the results and the execution times. To test the method, we considered four health states or conditions, namely flu, depression, pregnancy and eating disorders, and two locations, Portugal and Spain. We present the results obtained and demonstrate that the detection results and the performance of the method are improved after feature selection. The results are promising, with areas under the receiver operating characteristic curve between 0.7 and 0.9, and f-measure values around 0.8 and 0.9. This fact indicates that such approach provides a feasible solution for measuring and tracking the evolution of health states within the society.
DOI: 10.1371/journal.pone.0086191
PubMed: 24489699
PubMed Central: PMC3906034
Affiliations:
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Twitter: a good place to detect health conditions.</title><author><name sortKey="Prieto, Victor M" sort="Prieto, Victor M" uniqKey="Prieto V" first="Víctor M" last="Prieto">Víctor M. Prieto</name><affiliation wicri:level="1"><nlm:affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña</wicri:regionArea><wicri:noRegion>Coruña</wicri:noRegion></affiliation></author><author><name sortKey="Matos, Sergio" sort="Matos, Sergio" uniqKey="Matos S" first="Sérgio" last="Matos">Sérgio Matos</name><affiliation wicri:level="1"><nlm:affiliation>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro, Portugal.</nlm:affiliation><country xml:lang="fr">Portugal</country><wicri:regionArea>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro</wicri:regionArea><wicri:noRegion>Aveiro</wicri:noRegion></affiliation></author><author><name sortKey="Alvarez, Manuel" sort="Alvarez, Manuel" uniqKey="Alvarez M" first="Manuel" last="Álvarez">Manuel Álvarez</name><affiliation wicri:level="1"><nlm:affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña</wicri:regionArea><wicri:noRegion>Coruña</wicri:noRegion></affiliation></author><author><name sortKey="Cacheda, Fidel" sort="Cacheda, Fidel" uniqKey="Cacheda F" first="Fidel" last="Cacheda">Fidel Cacheda</name><affiliation wicri:level="1"><nlm:affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña</wicri:regionArea><wicri:noRegion>Coruña</wicri:noRegion></affiliation></author><author><name sortKey="Oliveira, Jose Luis" sort="Oliveira, Jose Luis" uniqKey="Oliveira J" first="José Luís" last="Oliveira">José Luís Oliveira</name><affiliation wicri:level="1"><nlm:affiliation>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro, Portugal.</nlm:affiliation><country xml:lang="fr">Portugal</country><wicri:regionArea>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro</wicri:regionArea><wicri:noRegion>Aveiro</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2014">2014</date><idno type="RBID">pubmed:24489699</idno><idno type="pmid">24489699</idno><idno type="doi">10.1371/journal.pone.0086191</idno><idno type="pmc">PMC3906034</idno><idno type="wicri:Area/Main/Corpus">00219</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Corpus" wicri:corpus="PubMed">00219</idno><idno type="wicri:Area/Main/Curation">000219</idno><idno type="wicri:explorRef" wicri:stream="Main" wicri:step="Curation">000219</idno><idno type="wicri:Area/Main/Exploration">000219</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Twitter: a good place to detect health conditions.</title><author><name sortKey="Prieto, Victor M" sort="Prieto, Victor M" uniqKey="Prieto V" first="Víctor M" last="Prieto">Víctor M. Prieto</name><affiliation wicri:level="1"><nlm:affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña</wicri:regionArea><wicri:noRegion>Coruña</wicri:noRegion></affiliation></author><author><name sortKey="Matos, Sergio" sort="Matos, Sergio" uniqKey="Matos S" first="Sérgio" last="Matos">Sérgio Matos</name><affiliation wicri:level="1"><nlm:affiliation>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro, Portugal.</nlm:affiliation><country xml:lang="fr">Portugal</country><wicri:regionArea>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro</wicri:regionArea><wicri:noRegion>Aveiro</wicri:noRegion></affiliation></author><author><name sortKey="Alvarez, Manuel" sort="Alvarez, Manuel" uniqKey="Alvarez M" first="Manuel" last="Álvarez">Manuel Álvarez</name><affiliation wicri:level="1"><nlm:affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña</wicri:regionArea><wicri:noRegion>Coruña</wicri:noRegion></affiliation></author><author><name sortKey="Cacheda, Fidel" sort="Cacheda, Fidel" uniqKey="Cacheda F" first="Fidel" last="Cacheda">Fidel Cacheda</name><affiliation wicri:level="1"><nlm:affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</nlm:affiliation><country xml:lang="fr">Espagne</country><wicri:regionArea>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña</wicri:regionArea><wicri:noRegion>Coruña</wicri:noRegion></affiliation></author><author><name sortKey="Oliveira, Jose Luis" sort="Oliveira, Jose Luis" uniqKey="Oliveira J" first="José Luís" last="Oliveira">José Luís Oliveira</name><affiliation wicri:level="1"><nlm:affiliation>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro, Portugal.</nlm:affiliation><country xml:lang="fr">Portugal</country><wicri:regionArea>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro</wicri:regionArea><wicri:noRegion>Aveiro</wicri:noRegion></affiliation></author></analytic><series><title level="j">PloS one</title><idno type="eISSN">1932-6203</idno><imprint><date when="2014" type="published">2014</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Artificial Intelligence (statistics & numerical data)</term><term>Blogging (statistics & numerical data)</term><term>Depression (epidemiology)</term><term>Feeding and Eating Disorders (epidemiology)</term><term>Female (MeSH)</term><term>Health Knowledge, Attitudes, Practice (MeSH)</term><term>Humans (MeSH)</term><term>Influenza, Human (epidemiology)</term><term>Portugal (epidemiology)</term><term>Pregnancy (MeSH)</term><term>ROC Curve (MeSH)</term><term>Spain (epidemiology)</term></keywords><keywords scheme="KwdFr" xml:lang="fr"><term>Connaissances, attitudes et pratiques en santé (MeSH)</term><term>Courbe ROC (MeSH)</term><term>Création de blogues (statistiques et données numériques)</term><term>Dépression (épidémiologie)</term><term>Espagne (épidémiologie)</term><term>Femelle (MeSH)</term><term>Grippe humaine (épidémiologie)</term><term>Grossesse (MeSH)</term><term>Humains (MeSH)</term><term>Intelligence artificielle (statistiques et données numériques)</term><term>Portugal (épidémiologie)</term><term>Troubles de l'alimentation (épidémiologie)</term></keywords><keywords scheme="MESH" qualifier="epidemiology" xml:lang="en"><term>Depression</term><term>Feeding and Eating Disorders</term><term>Influenza, Human</term><term>Portugal</term><term>Spain</term></keywords><keywords scheme="MESH" qualifier="statistics & numerical data" xml:lang="en"><term>Artificial Intelligence</term><term>Blogging</term></keywords><keywords scheme="MESH" qualifier="statistiques et données numériques" xml:lang="fr"><term>Création de blogues</term><term>Intelligence artificielle</term></keywords><keywords scheme="MESH" qualifier="épidémiologie" xml:lang="fr"><term>Dépression</term><term>Espagne</term><term>Grippe humaine</term><term>Portugal</term><term>Troubles de l'alimentation</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Female</term><term>Health Knowledge, Attitudes, Practice</term><term>Humans</term><term>Pregnancy</term><term>ROC Curve</term></keywords><keywords scheme="MESH" xml:lang="fr"><term>Connaissances, attitudes et pratiques en santé</term><term>Courbe ROC</term><term>Femelle</term><term>Grossesse</term><term>Humains</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">With the proliferation of social networks and blogs, the Internet is increasingly being used to disseminate personal health information rather than just as a source of information. In this paper we exploit the wealth of user-generated data, available through the micro-blogging service Twitter, to estimate and track the incidence of health conditions in society. The method is based on two stages: we start by extracting possibly relevant tweets using a set of specially crafted regular expressions, and then classify these initial messages using machine learning methods. Furthermore, we selected relevant features to improve the results and the execution times. To test the method, we considered four health states or conditions, namely flu, depression, pregnancy and eating disorders, and two locations, Portugal and Spain. We present the results obtained and demonstrate that the detection results and the performance of the method are improved after feature selection. The results are promising, with areas under the receiver operating characteristic curve between 0.7 and 0.9, and f-measure values around 0.8 and 0.9. This fact indicates that such approach provides a feasible solution for measuring and tracking the evolution of health states within the society. </div></front></TEI><pubmed><MedlineCitation Status="MEDLINE" Owner="NLM"><PMID Version="1">24489699</PMID><DateCompleted><Year>2014</Year><Month>09</Month><Day>29</Day></DateCompleted><DateRevised><Year>2018</Year><Month>12</Month><Day>02</Day></DateRevised><Article PubModel="Electronic-eCollection"><Journal><ISSN IssnType="Electronic">1932-6203</ISSN><JournalIssue CitedMedium="Internet"><Volume>9</Volume><Issue>1</Issue><PubDate><Year>2014</Year></PubDate></JournalIssue><Title>PloS one</Title><ISOAbbreviation>PLoS ONE</ISOAbbreviation></Journal><ArticleTitle>Twitter: a good place to detect health conditions.</ArticleTitle><Pagination><MedlinePgn>e86191</MedlinePgn></Pagination><ELocationID EIdType="doi" ValidYN="Y">10.1371/journal.pone.0086191</ELocationID><Abstract><AbstractText>With the proliferation of social networks and blogs, the Internet is increasingly being used to disseminate personal health information rather than just as a source of information. In this paper we exploit the wealth of user-generated data, available through the micro-blogging service Twitter, to estimate and track the incidence of health conditions in society. The method is based on two stages: we start by extracting possibly relevant tweets using a set of specially crafted regular expressions, and then classify these initial messages using machine learning methods. Furthermore, we selected relevant features to improve the results and the execution times. To test the method, we considered four health states or conditions, namely flu, depression, pregnancy and eating disorders, and two locations, Portugal and Spain. We present the results obtained and demonstrate that the detection results and the performance of the method are improved after feature selection. The results are promising, with areas under the receiver operating characteristic curve between 0.7 and 0.9, and f-measure values around 0.8 and 0.9. This fact indicates that such approach provides a feasible solution for measuring and tracking the evolution of health states within the society. </AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Prieto</LastName><ForeName>Víctor M</ForeName><Initials>VM</Initials><AffiliationInfo><Affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Matos</LastName><ForeName>Sérgio</ForeName><Initials>S</Initials><AffiliationInfo><Affiliation>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro, Portugal.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Álvarez</LastName><ForeName>Manuel</ForeName><Initials>M</Initials><AffiliationInfo><Affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Cacheda</LastName><ForeName>Fidel</ForeName><Initials>F</Initials><AffiliationInfo><Affiliation>Department of Information and Communication Technologies, Campus Elviña s/n, Coruña, Spain.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>Oliveira</LastName><ForeName>José Luís</ForeName><Initials>JL</Initials><AffiliationInfo><Affiliation>University of Aveiro, DETI/IEETA, Campus Universitariá de Santiago, Aveiro, Portugal.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType><PublicationType UI="D013485">Research Support, Non-U.S. Gov't</PublicationType></PublicationTypeList><ArticleDate DateType="Electronic"><Year>2014</Year><Month>01</Month><Day>29</Day></ArticleDate></Article><MedlineJournalInfo><Country>United States</Country><MedlineTA>PLoS One</MedlineTA><NlmUniqueID>101285081</NlmUniqueID><ISSNLinking>1932-6203</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><MeshHeadingList><MeshHeading><DescriptorName UI="D001185" MajorTopicYN="N">Artificial Intelligence</DescriptorName><QualifierName UI="Q000706" MajorTopicYN="Y">statistics & numerical data</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D057218" MajorTopicYN="N">Blogging</DescriptorName><QualifierName UI="Q000706" MajorTopicYN="Y">statistics & numerical data</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D003863" MajorTopicYN="N">Depression</DescriptorName><QualifierName UI="Q000453" MajorTopicYN="N">epidemiology</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D001068" MajorTopicYN="N">Feeding and Eating Disorders</DescriptorName><QualifierName UI="Q000453" MajorTopicYN="N">epidemiology</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D005260" MajorTopicYN="N">Female</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D007722" MajorTopicYN="Y">Health Knowledge, Attitudes, Practice</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D006801" MajorTopicYN="N">Humans</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D007251" MajorTopicYN="N">Influenza, Human</DescriptorName><QualifierName UI="Q000453" MajorTopicYN="N">epidemiology</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D011174" MajorTopicYN="N">Portugal</DescriptorName><QualifierName UI="Q000453" MajorTopicYN="N">epidemiology</QualifierName></MeshHeading><MeshHeading><DescriptorName UI="D011247" MajorTopicYN="N">Pregnancy</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D012372" MajorTopicYN="N">ROC Curve</DescriptorName></MeshHeading><MeshHeading><DescriptorName UI="D013030" MajorTopicYN="N">Spain</DescriptorName><QualifierName UI="Q000453" MajorTopicYN="N">epidemiology</QualifierName></MeshHeading></MeshHeadingList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="received"><Year>2013</Year><Month>03</Month><Day>08</Day></PubMedPubDate><PubMedPubDate PubStatus="accepted"><Year>2013</Year><Month>12</Month><Day>10</Day></PubMedPubDate><PubMedPubDate PubStatus="entrez"><Year>2014</Year><Month>2</Month><Day>4</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2014</Year><Month>2</Month><Day>4</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2014</Year><Month>9</Month><Day>30</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>epublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">24489699</ArticleId><ArticleId IdType="doi">10.1371/journal.pone.0086191</ArticleId><ArticleId IdType="pii">PONE-D-13-10567</ArticleId><ArticleId IdType="pmc">PMC3906034</ArticleId></ArticleIdList><ReferenceList><Reference><Citation>Nature. 2009 Feb 19;457(7232):1012-4</Citation><ArticleIdList><ArticleId IdType="pubmed">19020500</ArticleId></ArticleIdList></Reference><Reference><Citation>Am J Infect Control. 2010 Apr;38(3):182-8</Citation><ArticleIdList><ArticleId IdType="pubmed">20347636</ArticleId></ArticleIdList></Reference><Reference><Citation>PLoS One. 2010;5(11):e14118</Citation><ArticleIdList><ArticleId IdType="pubmed">21124761</ArticleId></ArticleIdList></Reference><Reference><Citation>Resuscitation. 2013 Feb;84(2):206-12</Citation><ArticleIdList><ArticleId IdType="pubmed">23108239</ArticleId></ArticleIdList></Reference><Reference><Citation>J Dent Res. 2011 Sep;90(9):1047-51</Citation><ArticleIdList><ArticleId IdType="pubmed">21768306</ArticleId></ArticleIdList></Reference><Reference><Citation>Am J Trop Med Hyg. 2012 Jan;86(1):39-45</Citation><ArticleIdList><ArticleId IdType="pubmed">22232449</ArticleId></ArticleIdList></Reference><Reference><Citation>Transbound Emerg Dis. 2012 Jun;59(3):223-32</Citation><ArticleIdList><ArticleId IdType="pubmed">22182229</ArticleId></ArticleIdList></Reference><Reference><Citation>PLoS One. 2011;6(5):e19467</Citation><ArticleIdList><ArticleId IdType="pubmed">21573238</ArticleId></ArticleIdList></Reference></ReferenceList></PubmedData></pubmed><affiliations><list><country><li>Espagne</li><li>Portugal</li></country></list><tree><country name="Espagne"><noRegion><name sortKey="Prieto, Victor M" sort="Prieto, Victor M" uniqKey="Prieto V" first="Víctor M" last="Prieto">Víctor M. Prieto</name></noRegion><name sortKey="Alvarez, Manuel" sort="Alvarez, Manuel" uniqKey="Alvarez M" first="Manuel" last="Álvarez">Manuel Álvarez</name><name sortKey="Cacheda, Fidel" sort="Cacheda, Fidel" uniqKey="Cacheda F" first="Fidel" last="Cacheda">Fidel Cacheda</name></country><country name="Portugal"><noRegion><name sortKey="Matos, Sergio" sort="Matos, Sergio" uniqKey="Matos S" first="Sérgio" last="Matos">Sérgio Matos</name></noRegion><name sortKey="Oliveira, Jose Luis" sort="Oliveira, Jose Luis" uniqKey="Oliveira J" first="José Luís" last="Oliveira">José Luís Oliveira</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Sante/explor/GrippeEspagneV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000202 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000202 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Sante
|area= GrippeEspagneV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= pubmed:24489699
|texte= Twitter: a good place to detect health conditions.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:24489699" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \
| NlmPubMed2Wicri -a GrippeEspagneV1
| This area was generated with Dilib version V0.6.37. |  |