Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study

<h3>Background</h3><p dir="ltr">Tools used to appraise the credibility of health information are time-consuming to apply and require context-specific expertise, limiting their use for quickly identifying and mitigating the spread of misinformation as it emerges.</p>...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Zubair Shah (231886) (author)
مؤلفون آخرون: Didi Surian (5985425) (author), Amalie Dyda (5049590) (author), Enrico Coiera (64865) (author), Kenneth D Mandl (18461455) (author), Adam G Dunn (11560114) (author)
منشور في: 2019
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513514135093248
author Zubair Shah (231886)
author2 Didi Surian (5985425)
Amalie Dyda (5049590)
Enrico Coiera (64865)
Kenneth D Mandl (18461455)
Adam G Dunn (11560114)
author2_role author
author
author
author
author
author_facet Zubair Shah (231886)
Didi Surian (5985425)
Amalie Dyda (5049590)
Enrico Coiera (64865)
Kenneth D Mandl (18461455)
Adam G Dunn (11560114)
author_role author
dc.creator.none.fl_str_mv Zubair Shah (231886)
Didi Surian (5985425)
Amalie Dyda (5049590)
Enrico Coiera (64865)
Kenneth D Mandl (18461455)
Adam G Dunn (11560114)
dc.date.none.fl_str_mv 2019-11-04T03:00:00Z
dc.identifier.none.fl_str_mv 10.2196/14007
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Automatically_Appraising_the_Credibility_of_Vaccine-Related_Web_Pages_Shared_on_Social_Media_A_Twitter_Surveillance_Study/25904140
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Education
Curriculum and pedagogy
health misinformation
credibility appraisal
machine learning
social media
dc.title.none.fl_str_mv Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <h3>Background</h3><p dir="ltr">Tools used to appraise the credibility of health information are time-consuming to apply and require context-specific expertise, limiting their use for quickly identifying and mitigating the spread of misinformation as it emerges.</p><h3>Objective</h3><p dir="ltr">The aim of this study was to estimate the proportion of vaccine-related Twitter posts linked to Web pages of low credibility and measure the potential reach of those posts.</p><h3>Methods</h3><p dir="ltr">Sampling from 143,003 unique vaccine-related Web pages shared on Twitter between January 2017 and March 2018, we used a 7-point checklist adapted from validated tools and guidelines to manually appraise the credibility of 474 Web pages. These were used to train several classifiers (random forests, support vector machines, and recurrent neural networks) using the text from a Web page to predict whether the information satisfies each of the 7 criteria. Estimating the credibility of all other Web pages, we used the follower network to estimate potential exposures relative to a credibility score defined by the 7-point checklist.</p><h3>Results</h3><p dir="ltr">The best-performing classifiers were able to distinguish between low, medium, and high credibility with an accuracy of 78% and labeled low-credibility Web pages with a precision of over 96%. Across the set of unique Web pages, 11.86% (16,961 of 143,003) were estimated as low credibility and they generated 9.34% (1.64 billion of 17.6 billion) of potential exposures. The 100 most popular links to low credibility Web pages were each potentially seen by an estimated 2 million to 80 million Twitter users globally.</p><h3>Conclusions</h3><p dir="ltr">The results indicate that although a small minority of low-credibility Web pages reach a large audience, low-credibility Web pages tend to reach fewer users than other Web pages overall and are more commonly shared within certain subpopulations. An automatic credibility appraisal tool may be useful for finding communities of users at higher risk of exposure to low-credibility vaccine communications.</p><h2>Other Information</h2><p dir="ltr">Published in: Journal of Medical Internet Research<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.2196/14007" target="_blank">https://dx.doi.org/10.2196/14007</a></p>
eu_rights_str_mv openAccess
id Manara2_01d0d13f00438c90cc24b67ad173e9b3
identifier_str_mv 10.2196/14007
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25904140
publishDate 2019
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance StudyZubair Shah (231886)Didi Surian (5985425)Amalie Dyda (5049590)Enrico Coiera (64865)Kenneth D Mandl (18461455)Adam G Dunn (11560114)EducationCurriculum and pedagogyhealth misinformationcredibility appraisalmachine learningsocial media<h3>Background</h3><p dir="ltr">Tools used to appraise the credibility of health information are time-consuming to apply and require context-specific expertise, limiting their use for quickly identifying and mitigating the spread of misinformation as it emerges.</p><h3>Objective</h3><p dir="ltr">The aim of this study was to estimate the proportion of vaccine-related Twitter posts linked to Web pages of low credibility and measure the potential reach of those posts.</p><h3>Methods</h3><p dir="ltr">Sampling from 143,003 unique vaccine-related Web pages shared on Twitter between January 2017 and March 2018, we used a 7-point checklist adapted from validated tools and guidelines to manually appraise the credibility of 474 Web pages. These were used to train several classifiers (random forests, support vector machines, and recurrent neural networks) using the text from a Web page to predict whether the information satisfies each of the 7 criteria. Estimating the credibility of all other Web pages, we used the follower network to estimate potential exposures relative to a credibility score defined by the 7-point checklist.</p><h3>Results</h3><p dir="ltr">The best-performing classifiers were able to distinguish between low, medium, and high credibility with an accuracy of 78% and labeled low-credibility Web pages with a precision of over 96%. Across the set of unique Web pages, 11.86% (16,961 of 143,003) were estimated as low credibility and they generated 9.34% (1.64 billion of 17.6 billion) of potential exposures. The 100 most popular links to low credibility Web pages were each potentially seen by an estimated 2 million to 80 million Twitter users globally.</p><h3>Conclusions</h3><p dir="ltr">The results indicate that although a small minority of low-credibility Web pages reach a large audience, low-credibility Web pages tend to reach fewer users than other Web pages overall and are more commonly shared within certain subpopulations. An automatic credibility appraisal tool may be useful for finding communities of users at higher risk of exposure to low-credibility vaccine communications.</p><h2>Other Information</h2><p dir="ltr">Published in: Journal of Medical Internet Research<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.2196/14007" target="_blank">https://dx.doi.org/10.2196/14007</a></p>2019-11-04T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.2196/14007https://figshare.com/articles/journal_contribution/Automatically_Appraising_the_Credibility_of_Vaccine-Related_Web_Pages_Shared_on_Social_Media_A_Twitter_Surveillance_Study/25904140CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/259041402019-11-04T03:00:00Z
spellingShingle Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study
Zubair Shah (231886)
Education
Curriculum and pedagogy
health misinformation
credibility appraisal
machine learning
social media
status_str publishedVersion
title Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study
title_full Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study
title_fullStr Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study
title_full_unstemmed Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study
title_short Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study
title_sort Automatically Appraising the Credibility of Vaccine-Related Web Pages Shared on Social Media: A Twitter Surveillance Study
topic Education
Curriculum and pedagogy
health misinformation
credibility appraisal
machine learning
social media