MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter

Wu, Cheng-Lin; Hsieh, Hsun-Ping; Jiang, Jiawei; Yang, Yi-Chieh; Shei, Chris; Chen, Yu-Wen

doi:10.3390/app12010453

Journal article 502 views 78 downloads

MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter

Cheng-Lin Wu, Hsun-Ping Hsieh, Jiawei Jiang, Yi-Chieh Yang, Chris Shei

, Yu-Wen Chen

Applied Sciences, Volume: 12, Issue: 1, Start page: 453

Swansea University Author: Chris Shei

PDF | Version of Record

Copyright: © 2022 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license
Download (1.73MB)

Check full text

DOI (Published version): 10.3390/app12010453

Abstract

To alleviate the impact of fake news on our society, predicting the popularity of fake news posts on social media is a crucial problem worthy of study. However, most related studies on fake news emphasize detection only. In this paper, we focus on the issue of fake news influence prediction, i.e., i...

Full description

Published in:	Applied Sciences
ISSN:	2076-3417
Published:	MDPI AG 2022
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa59136
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2022-01-10T15:45:02Z
last_indexed	2022-01-19T04:28:59Z
id	cronfa59136
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2022-01-18T16:05:06.6468082</datestamp><bib-version>v2</bib-version><id>59136</id><entry>2022-01-10</entry><title>MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter</title><swanseaauthors><author><sid>dda146db4c8e427bf10a4a822e14ed54</sid><ORCID>0000-0002-2313-4365</ORCID><firstname>Chris</firstname><surname>Shei</surname><name>Chris Shei</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-01-10</date><deptcode>APLI</deptcode><abstract>To alleviate the impact of fake news on our society, predicting the popularity of fake news posts on social media is a crucial problem worthy of study. However, most related studies on fake news emphasize detection only. In this paper, we focus on the issue of fake news influence prediction, i.e., inferring how popular a fake news post might become on social platforms. To achieve our goal, we propose a comprehensive framework, MUFFLE, which captures multi-modal dynamics by encoding the representation of news-related social networks, user characteristics, and content in text. The attention mechanism developed in the model can provide explainability for social or psychological analysis. To examine the effectiveness of MUFFLE, we conducted extensive experiments on real-world datasets. The experimental results show that our proposed method outperforms both state-of-the-art methods of popularity prediction and machine-based baselines in top-k NDCG and hit rate. Through the experiments, we also analyze the feature importance for predicting fake news influence via the explainability provided by MUFFLE.</abstract><type>Journal Article</type><journal>Applied Sciences</journal><volume>12</volume><journalNumber>1</journalNumber><paginationStart>453</paginationStart><paginationEnd/><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2076-3417</issnElectronic><keywords>fake news, influence estimator, multi-model, text mining</keywords><publishedDay>4</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-01-04</publishedDate><doi>10.3390/app12010453</doi><url/><notes/><college>COLLEGE NANME</college><department>Applied Linguistics</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>APLI</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This research was funded by the Ministry of Science and Technology (MOST) of Taiwan under grants MOST 109-2636-E-006-025 and MOST 110-2636-E-006-011</funders><lastEdited>2022-01-18T16:05:06.6468082</lastEdited><Created>2022-01-10T15:42:38.1345150</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Culture and Communication - English Language, Tesol, Applied Linguistics</level></path><authors><author><firstname>Cheng-Lin</firstname><surname>Wu</surname><order>1</order></author><author><firstname>Hsun-Ping</firstname><surname>Hsieh</surname><order>2</order></author><author><firstname>Jiawei</firstname><surname>Jiang</surname><order>3</order></author><author><firstname>Yi-Chieh</firstname><surname>Yang</surname><order>4</order></author><author><firstname>Chris</firstname><surname>Shei</surname><orcid>0000-0002-2313-4365</orcid><order>5</order></author><author><firstname>Yu-Wen</firstname><surname>Chen</surname><order>6</order></author></authors><documents><document><filename>59136__22100__04a1e6e95e7d4a1b8021180a99b80c7d.pdf</filename><originalFilename>applsci-12-00453.pdf</originalFilename><uploaded>2022-01-10T15:42:38.1344705</uploaded><type>Output</type><contentLength>1818498</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: © 2022 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2022-01-18T16:05:06.6468082 v2 59136 2022-01-10 MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter dda146db4c8e427bf10a4a822e14ed54 0000-0002-2313-4365 Chris Shei Chris Shei true false 2022-01-10 APLI To alleviate the impact of fake news on our society, predicting the popularity of fake news posts on social media is a crucial problem worthy of study. However, most related studies on fake news emphasize detection only. In this paper, we focus on the issue of fake news influence prediction, i.e., inferring how popular a fake news post might become on social platforms. To achieve our goal, we propose a comprehensive framework, MUFFLE, which captures multi-modal dynamics by encoding the representation of news-related social networks, user characteristics, and content in text. The attention mechanism developed in the model can provide explainability for social or psychological analysis. To examine the effectiveness of MUFFLE, we conducted extensive experiments on real-world datasets. The experimental results show that our proposed method outperforms both state-of-the-art methods of popularity prediction and machine-based baselines in top-k NDCG and hit rate. Through the experiments, we also analyze the feature importance for predicting fake news influence via the explainability provided by MUFFLE. Journal Article Applied Sciences 12 1 453 MDPI AG 2076-3417 fake news, influence estimator, multi-model, text mining 4 1 2022 2022-01-04 10.3390/app12010453 COLLEGE NANME Applied Linguistics COLLEGE CODE APLI Swansea University This research was funded by the Ministry of Science and Technology (MOST) of Taiwan under grants MOST 109-2636-E-006-025 and MOST 110-2636-E-006-011 2022-01-18T16:05:06.6468082 2022-01-10T15:42:38.1345150 Faculty of Humanities and Social Sciences School of Culture and Communication - English Language, Tesol, Applied Linguistics Cheng-Lin Wu 1 Hsun-Ping Hsieh 2 Jiawei Jiang 3 Yi-Chieh Yang 4 Chris Shei 0000-0002-2313-4365 5 Yu-Wen Chen 6 59136__22100__04a1e6e95e7d4a1b8021180a99b80c7d.pdf applsci-12-00453.pdf 2022-01-10T15:42:38.1344705 Output 1818498 application/pdf Version of Record true Copyright: © 2022 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license true eng https://creativecommons.org/licenses/by/4.0/
title	MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter
spellingShingle	MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter Chris Shei
title_short	MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter
title_full	MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter
title_fullStr	MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter
title_full_unstemmed	MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter
title_sort	MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter
author_id_str_mv	dda146db4c8e427bf10a4a822e14ed54
author_id_fullname_str_mv	dda146db4c8e427bf10a4a822e14ed54_***_Chris Shei
author	Chris Shei
author2	Cheng-Lin Wu Hsun-Ping Hsieh Jiawei Jiang Yi-Chieh Yang Chris Shei Yu-Wen Chen
format	Journal article
container_title	Applied Sciences
container_volume	12
container_issue	1
container_start_page	453
publishDate	2022
institution	Swansea University
issn	2076-3417
doi_str_mv	10.3390/app12010453
publisher	MDPI AG
college_str	Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id	facultyofhumanitiesandsocialsciences
hierarchy_top_title	Faculty of Humanities and Social Sciences
hierarchy_parent_id	facultyofhumanitiesandsocialsciences
hierarchy_parent_title	Faculty of Humanities and Social Sciences
department_str	School of Culture and Communication - English Language, Tesol, Applied Linguistics{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Culture and Communication - English Language, Tesol, Applied Linguistics
document_store_str	1
active_str	0
description	To alleviate the impact of fake news on our society, predicting the popularity of fake news posts on social media is a crucial problem worthy of study. However, most related studies on fake news emphasize detection only. In this paper, we focus on the issue of fake news influence prediction, i.e., inferring how popular a fake news post might become on social platforms. To achieve our goal, we propose a comprehensive framework, MUFFLE, which captures multi-modal dynamics by encoding the representation of news-related social networks, user characteristics, and content in text. The attention mechanism developed in the model can provide explainability for social or psychological analysis. To examine the effectiveness of MUFFLE, we conducted extensive experiments on real-world datasets. The experimental results show that our proposed method outperforms both state-of-the-art methods of popularity prediction and machine-based baselines in top-k NDCG and hit rate. Through the experiments, we also analyze the feature importance for predicting fake news influence via the explainability provided by MUFFLE.
published_date	2022-01-04T04:16:12Z
_version_	1763754086526615552
score	11.012947

MUFFLE: Multi-Modal Fake News Influence Estimator on Twitter

Similar Items