No Cover Image

Conference Paper/Proceeding/Abstract 555 views

Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos

Nicholas Micallef Orcid Logo, Marcelo Sandoval-Castañeda, Adi Cohen, Mustaque Ahamad, Srijan Kumar, Nasir Memon

Proceedings of the Sixteenth International AAAI Conference on Web and Social Media, Volume: 16, Start page: 651-662

Swansea University Author: Nicholas Micallef Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

Abstract

Social media posts that direct users to YouTube videos are one of the most effective techniques for spreading misinformation. However, it has been observed that such posts rarely get deleted or flagged. Since multi-modal misinformation that leads to compelling videos has more impact than using just...

Full description

Published in: Proceedings of the Sixteenth International AAAI Conference on Web and Social Media
ISBN: 13 978-1-57735-875-6 10 1-57735-875-9
ISSN: 2162-3449 2334-0770
Published: 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa60586
first_indexed 2022-08-18T10:45:32Z
last_indexed 2024-11-14T12:17:37Z
id cronfa60586
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2024-07-11T14:37:48.4390786</datestamp><bib-version>v2</bib-version><id>60586</id><entry>2022-07-21</entry><title>Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos</title><swanseaauthors><author><sid>1cc4c84582d665b7ee08fb16f5454671</sid><ORCID>0000-0002-2683-8042</ORCID><firstname>Nicholas</firstname><surname>Micallef</surname><name>Nicholas Micallef</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-07-21</date><deptcode>MACS</deptcode><abstract>Social media posts that direct users to YouTube videos are one of the most effective techniques for spreading misinformation. However, it has been observed that such posts rarely get deleted or flagged. Since multi-modal misinformation that leads to compelling videos has more impact than using just textual content, it is important to characterize and detect such textual post and video pairs to prevent users from becoming victims of misinformation. To address this gap, we build a taxonomy of how links to YouTube videos are used on social media platforms. We then use pairs of posts and videos annotated with this taxonomy to test several classification models built using cross-platform features. Our work reveals several characteristics of post-video pairs, in terms of how posts and videos are related to each other, the type of content they share, and their collective outcome. In addition, we find that traditional approaches to misinformation detection that rely only on text from posts miss a significant number of post-video pairs that contain misinformation. More importantly, we find that to reduce the spread of misinformation via post-video pairs, classifiers would be more effective if they are designed to use data and features from multiple diverse platforms.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>Proceedings of the Sixteenth International AAAI Conference on Web and Social Media</journal><volume>16</volume><journalNumber/><paginationStart>651-662</paginationStart><paginationEnd/><publisher/><placeOfPublication/><isbnPrint>13 978-1-57735-875-6</isbnPrint><isbnElectronic>10 1-57735-875-9</isbnElectronic><issnPrint>2162-3449</issnPrint><issnElectronic>2334-0770</issnElectronic><keywords/><publishedDay>1</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-06-01</publishedDate><doi/><url>https://ojs.aaai.org/index.php/ICWSM/article/view/19323</url><notes>https://ojs.aaai.org/index.php/ICWSM/article/view/19323</notes><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2024-07-11T14:37:48.4390786</lastEdited><Created>2022-07-21T16:15:55.2768151</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Nicholas</firstname><surname>Micallef</surname><orcid>0000-0002-2683-8042</orcid><order>1</order></author><author><firstname>Marcelo</firstname><surname>Sandoval-Casta&#xF1;eda</surname><order>2</order></author><author><firstname>Adi</firstname><surname>Cohen</surname><order>3</order></author><author><firstname>Mustaque</firstname><surname>Ahamad</surname><order>4</order></author><author><firstname>Srijan</firstname><surname>Kumar</surname><order>5</order></author><author><firstname>Nasir</firstname><surname>Memon</surname><order>6</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2024-07-11T14:37:48.4390786 v2 60586 2022-07-21 Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos 1cc4c84582d665b7ee08fb16f5454671 0000-0002-2683-8042 Nicholas Micallef Nicholas Micallef true false 2022-07-21 MACS Social media posts that direct users to YouTube videos are one of the most effective techniques for spreading misinformation. However, it has been observed that such posts rarely get deleted or flagged. Since multi-modal misinformation that leads to compelling videos has more impact than using just textual content, it is important to characterize and detect such textual post and video pairs to prevent users from becoming victims of misinformation. To address this gap, we build a taxonomy of how links to YouTube videos are used on social media platforms. We then use pairs of posts and videos annotated with this taxonomy to test several classification models built using cross-platform features. Our work reveals several characteristics of post-video pairs, in terms of how posts and videos are related to each other, the type of content they share, and their collective outcome. In addition, we find that traditional approaches to misinformation detection that rely only on text from posts miss a significant number of post-video pairs that contain misinformation. More importantly, we find that to reduce the spread of misinformation via post-video pairs, classifiers would be more effective if they are designed to use data and features from multiple diverse platforms. Conference Paper/Proceeding/Abstract Proceedings of the Sixteenth International AAAI Conference on Web and Social Media 16 651-662 13 978-1-57735-875-6 10 1-57735-875-9 2162-3449 2334-0770 1 6 2022 2022-06-01 https://ojs.aaai.org/index.php/ICWSM/article/view/19323 https://ojs.aaai.org/index.php/ICWSM/article/view/19323 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University 2024-07-11T14:37:48.4390786 2022-07-21T16:15:55.2768151 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Nicholas Micallef 0000-0002-2683-8042 1 Marcelo Sandoval-Castañeda 2 Adi Cohen 3 Mustaque Ahamad 4 Srijan Kumar 5 Nasir Memon 6
title Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos
spellingShingle Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos
Nicholas Micallef
title_short Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos
title_full Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos
title_fullStr Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos
title_full_unstemmed Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos
title_sort Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos
author_id_str_mv 1cc4c84582d665b7ee08fb16f5454671
author_id_fullname_str_mv 1cc4c84582d665b7ee08fb16f5454671_***_Nicholas Micallef
author Nicholas Micallef
author2 Nicholas Micallef
Marcelo Sandoval-Castañeda
Adi Cohen
Mustaque Ahamad
Srijan Kumar
Nasir Memon
format Conference Paper/Proceeding/Abstract
container_title Proceedings of the Sixteenth International AAAI Conference on Web and Social Media
container_volume 16
container_start_page 651-662
publishDate 2022
institution Swansea University
isbn 13 978-1-57735-875-6
10 1-57735-875-9
issn 2162-3449
2334-0770
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url https://ojs.aaai.org/index.php/ICWSM/article/view/19323
document_store_str 0
active_str 0
description Social media posts that direct users to YouTube videos are one of the most effective techniques for spreading misinformation. However, it has been observed that such posts rarely get deleted or flagged. Since multi-modal misinformation that leads to compelling videos has more impact than using just textual content, it is important to characterize and detect such textual post and video pairs to prevent users from becoming victims of misinformation. To address this gap, we build a taxonomy of how links to YouTube videos are used on social media platforms. We then use pairs of posts and videos annotated with this taxonomy to test several classification models built using cross-platform features. Our work reveals several characteristics of post-video pairs, in terms of how posts and videos are related to each other, the type of content they share, and their collective outcome. In addition, we find that traditional approaches to misinformation detection that rely only on text from posts miss a significant number of post-video pairs that contain misinformation. More importantly, we find that to reduce the spread of misinformation via post-video pairs, classifiers would be more effective if they are designed to use data and features from multiple diverse platforms.
published_date 2022-06-01T08:17:57Z
_version_ 1822117517578993664
score 11.048453

Similar Items