Who can verify this? Finding authorities for rumor verification in Twitter

<p>A large body of research work has proposed verification techniques for rumors spreading in social media that mainly relied on subjective evidence, e.g., propagation networks or user interactions. Alternatively, in this work, we introduce the task of authority finding in social media, in whi...

Full description

Saved in:
Bibliographic Details
Main Author: Fatima Haouari (17100181) (author)
Other Authors: Tamer Elsayed (14777071) (author), Watheq Mansour (17863058) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513528975589376
author Fatima Haouari (17100181)
author2 Tamer Elsayed (14777071)
Watheq Mansour (17863058)
author2_role author
author
author_facet Fatima Haouari (17100181)
Tamer Elsayed (14777071)
Watheq Mansour (17863058)
author_role author
dc.creator.none.fl_str_mv Fatima Haouari (17100181)
Tamer Elsayed (14777071)
Watheq Mansour (17863058)
dc.date.none.fl_str_mv 2023-07-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.ipm.2023.103366
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Who_can_verify_this_Finding_authorities_for_rumor_verification_in_Twitter/25101296
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Information systems
Library and information studies
Expert finding
Social media
Arabic tweets
Test collection
Claim expansion
dc.title.none.fl_str_mv Who can verify this? Finding authorities for rumor verification in Twitter
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>A large body of research work has proposed verification techniques for rumors spreading in social media that mainly relied on subjective evidence, e.g., propagation networks or user interactions. Alternatively, in this work, we introduce the task of authority finding in social media, in which we aim to find authorities, for given rumors spreading specifically in Twitter, who can help verify them by providing exclusive/convincing evidence that supports or denies those rumors. We release the first test collection for Authority FINding in Arabic Twitter (AuFIN). The collection comprises 150 rumors (expressed in tweets) associated with a total of 1,044 authority accounts and a user collection of 395,231 Twitter accounts (members of 1,192,284 unique Twitter lists). Moreover, we propose a hybrid model that employs pre-trained language models and combines lexical, semantic, and network signals to find authorities. Our experiments show that the textual representation of users is insufficient, and incorporating the Twitter network features improved the recall of authorities by 34%. Moreover, semantic ranking is inferior to the lexical and network-based ranking in terms of precision, but superior in terms of recall. Therefore, combining both the semantic and network-based ranking achieved the best overall performance achieving a precision of 0.413 and 0.213 at depth 1 and 5 respectively. We show that rumor expansion by exploiting Knowledge Bases improves the recall of authorities by up to 15%. Furthermore, we find that SOTA models for topic expert finding perform poorly on finding authorities. Finally, drawing upon our experiments, we discuss failure factors and make recommendations for future research directions in addressing this task.</p><h2>Other Information</h2> <p> Published in: Information Processing & Management<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.ipm.2023.103366" target="_blank">https://dx.doi.org/10.1016/j.ipm.2023.103366</a></p>
eu_rights_str_mv openAccess
id Manara2_a56549b06cb78bcbf091bfb6f2f9563e
identifier_str_mv 10.1016/j.ipm.2023.103366
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25101296
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Who can verify this? Finding authorities for rumor verification in TwitterFatima Haouari (17100181)Tamer Elsayed (14777071)Watheq Mansour (17863058)Information and computing sciencesInformation systemsLibrary and information studiesExpert findingSocial mediaArabic tweetsTest collectionClaim expansion<p>A large body of research work has proposed verification techniques for rumors spreading in social media that mainly relied on subjective evidence, e.g., propagation networks or user interactions. Alternatively, in this work, we introduce the task of authority finding in social media, in which we aim to find authorities, for given rumors spreading specifically in Twitter, who can help verify them by providing exclusive/convincing evidence that supports or denies those rumors. We release the first test collection for Authority FINding in Arabic Twitter (AuFIN). The collection comprises 150 rumors (expressed in tweets) associated with a total of 1,044 authority accounts and a user collection of 395,231 Twitter accounts (members of 1,192,284 unique Twitter lists). Moreover, we propose a hybrid model that employs pre-trained language models and combines lexical, semantic, and network signals to find authorities. Our experiments show that the textual representation of users is insufficient, and incorporating the Twitter network features improved the recall of authorities by 34%. Moreover, semantic ranking is inferior to the lexical and network-based ranking in terms of precision, but superior in terms of recall. Therefore, combining both the semantic and network-based ranking achieved the best overall performance achieving a precision of 0.413 and 0.213 at depth 1 and 5 respectively. We show that rumor expansion by exploiting Knowledge Bases improves the recall of authorities by up to 15%. Furthermore, we find that SOTA models for topic expert finding perform poorly on finding authorities. Finally, drawing upon our experiments, we discuss failure factors and make recommendations for future research directions in addressing this task.</p><h2>Other Information</h2> <p> Published in: Information Processing & Management<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.ipm.2023.103366" target="_blank">https://dx.doi.org/10.1016/j.ipm.2023.103366</a></p>2023-07-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.ipm.2023.103366https://figshare.com/articles/journal_contribution/Who_can_verify_this_Finding_authorities_for_rumor_verification_in_Twitter/25101296CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/251012962023-07-01T00:00:00Z
spellingShingle Who can verify this? Finding authorities for rumor verification in Twitter
Fatima Haouari (17100181)
Information and computing sciences
Information systems
Library and information studies
Expert finding
Social media
Arabic tweets
Test collection
Claim expansion
status_str publishedVersion
title Who can verify this? Finding authorities for rumor verification in Twitter
title_full Who can verify this? Finding authorities for rumor verification in Twitter
title_fullStr Who can verify this? Finding authorities for rumor verification in Twitter
title_full_unstemmed Who can verify this? Finding authorities for rumor verification in Twitter
title_short Who can verify this? Finding authorities for rumor verification in Twitter
title_sort Who can verify this? Finding authorities for rumor verification in Twitter
topic Information and computing sciences
Information systems
Library and information studies
Expert finding
Social media
Arabic tweets
Test collection
Claim expansion