Who Says What in Which Networks: What influences Social Media Users’ Emotional Reactions to the COVID-19 Vaccine Infodemic? DOI
Aimei Yang, Jieun Shin, Hye Min Kim

и другие.

Social Science Computer Review, Год журнала: 2022, Номер 41(6), С. 1986 - 2009

Опубликована: Сен. 24, 2022

This study aims to identify effective predictors that influence publics’ emotional reactions COVID-19 vaccine misinformation as well corrective messages. We collected a large sample of related and messages on Facebook the users’ (i.e., emojis) these Focusing three clusters features such messages’ linguistic features, source characteristics, network positions, we examined whether information would differ. used random forest models most salient among over 70 for both types Our analysis found misinformation, political ideology message was feature predicted anxious enthusiastic reactions, followed by highlight personal concerns positions. For messages, while sources’ still key raising anxiety, important triggering enthusiasm positions quality.

Язык: Английский

Dual emotion based fake news detection: A deep attention-weight update approach DOI
Alex Munyole Luvembe, Weimin Li, Shaohua Li

и другие.

Information Processing & Management, Год журнала: 2023, Номер 60(4), С. 103354 - 103354

Опубликована: Март 31, 2023

Язык: Английский

Процитировано

76
Fake News Detection Model on Social Media by Leveraging Sentiment Analysis of News Content and Emotion Analysis of Users’ Comments DOI Creative Commons
Suhaib Kh. Hamed,

Mohd Juzaiddin Ab Aziz,

Mohd Ridzwan Yaakub

и другие.

Sensors, Год журнала: 2023, Номер 23(4), С. 1748 - 1748

Опубликована: Фев. 4, 2023

Nowadays, social media has become the main source of news around world. The spread fake on networks a serious global issue, damaging many aspects, such as political, economic, and negatively affecting lives citizens. Fake often carries negative sentiments, public's response to it emotions surprise, fear, disgust. In this article, we extracted features based sentiment analysis articles emotion users' comments regarding news. These were fed, along with content feature news, proposed bidirectional long short-term memory model detect We used standard Fakeddit dataset that contains titles posted them train test model. suggested model, using features, provided high detection accuracy 96.77% Area under ROC Curve measure, which is higher than what other state-of-the-art studies offer. results prove represents publisher's stance, comments, represent crowd's contribute raising efficiency

Язык: Английский

Процитировано

44
A Scientometric Analysis of Deep Learning Approaches for Detecting Fake News DOI Open Access
Pummy Dhiman, Amandeep Kaur, Celestine Iwendi

и другие.

Electronics, Год журнала: 2023, Номер 12(4), С. 948 - 948

Опубликована: Фев. 14, 2023

The unregulated proliferation of counterfeit news creation and dissemination that has been seen in recent years poses a constant threat to democracy. Fake articles have the power persuade individuals, leaving them perplexed. This scientometric study examined 569 documents from Scopus database between 2012 mid-2022 look for general research trends, publication citation structures, authorship collaboration patterns, bibliographic coupling, productivity patterns order identify fake using deep learning. For this study, Biblioshiny VOSviewer were used. findings clearly demonstrate trend toward an increase publications since 2016, is still issue global perspective. Thematic analysis papers reveals topics related social media surveillance monitoring public attitudes perceptions, as well news, are crucial but underdeveloped, while studies on detection, digital contents, forensics, computer vision constitute niche areas. Furthermore, results show China USA strongest international collaboration, despite India writing more articles. paper also examines current state art learning techniques with goal providing potential roadmap researchers interested undertaking field.

Язык: Английский

Процитировано

43
Linguistic features based framework for automatic fake news detection DOI
Sonal Garg, Dilip Kumar Sharma

Computers & Industrial Engineering, Год журнала: 2022, Номер 172, С. 108432 - 108432

Опубликована: Июль 9, 2022

Язык: Английский

Процитировано

39
Mapping the Landscape of Misinformation Detection: A Bibliometric Approach DOI Creative Commons
Andra Sandu,

Ioana Ioanăș,

Camelia Delcea

и другие.

Information, Год журнала: 2024, Номер 15(1), С. 60 - 60

Опубликована: Янв. 19, 2024

The proliferation of misinformation presents a significant challenge in today’s information landscape, impacting various aspects society. While is often confused with terms like disinformation and fake news, it crucial to distinguish that involves, mostcases, inaccurate without the intent cause harm. In some instances, individuals unwittingly share misinformation, driven by desire assist others thorough research. However, there are also situations where involves negligence, or even intentional manipulation, aim shaping opinions decisions target audience. Another key factor contributing its alignment individual beliefs emotions. This magnifies impact influence as people tend seek reinforces their existing beliefs. As starting point, 56 papers containing ‘misinformation detection’ title, abstract, keywords, marked “articles”, written English, published between 2016 2022, were extracted from Web Science platform further analyzed using Biblioshiny. bibliometric study aims offer comprehensive perspective on field detection examining evolution identifying emerging trends, influential authors, collaborative networks, highly cited articles, terms, institutional affiliations, themes, other relevant factors. Additionally, reviews most provides an overview all selected dataset, shedding light methods employed counter primary research areas has been explored, including sources such online social communities, news platforms. Recent events related health issues stemming COVID-19 pandemic have heightened interest within community regarding detection, statistic which supported fact half included top 10 based number citations addressed this subject. insights derived analysis contribute valuable knowledge address issue, enhancing our understanding field’s dynamics aiding development effective strategies detect mitigate misinformation. results spotlight IEEE Access occupies first position current papers, King Saud University listed contributor for while countries, top-5 list highest contribution area made USA, India, China, Spain, UK. Moreover, supports promotion verified reliable data, fostering more informed trustworthy environment.

Язык: Английский

Процитировано

13
Emotion detection for misinformation: A review DOI Creative Commons
Zhiwei Liu, Tianlin Zhang, Kailai Yang

и другие.

Information Fusion, Год журнала: 2024, Номер 107, С. 102300 - 102300

Опубликована: Фев. 12, 2024

Язык: Английский

Процитировано

10
BCMF: A bidirectional cross-modal fusion model for fake news detection DOI
Chuanming Yu,

MA Yin-xue,

Lu An

и другие.

Information Processing & Management, Год журнала: 2022, Номер 59(5), С. 103063 - 103063

Опубликована: Авг. 19, 2022

Язык: Английский

Процитировано

24
Spanish Corpora of tweets about COVID-19 vaccination for automatic stance detection DOI Creative Commons
Rubén Yáñez Martínez, Guillermo Blanco, Anália Lourenço

и другие.

Information Processing & Management, Год журнала: 2023, Номер 60(3), С. 103294 - 103294

Опубликована: Янв. 30, 2023

The paper presents new annotated corpora for performing stance detection on Spanish Twitter data, most notably Health-related tweets. objectives of this research are threefold: (1) to develop a manually benchmark corpus emotion recognition taking into account different variants in social posts; (2) evaluate the efficiency semi-supervised models extending such with unlabelled and (3) describe short text via specialised topic modelling. A 2,801 tweets about COVID-19 vaccination was by three native speakers be favour (904), against (674) or neither (1,223) 0.725 Fleiss’ kappa score. Results show that self-training method SVM base estimator can alleviate annotation work while ensuring high model performance. outperformed other approaches produced 11,204 macro averaged f1 score 0.94. combination sentence-level deep learning embeddings density-based clustering applied explore contents both corpora. Topic quality measured terms trustworthiness validation index.

Язык: Английский

Процитировано

16
Unveiling the truth: A systematic review of fact-checking and fake news research in social sciences DOI Open Access
Santiago Tejedor, Luis M. Romero-Rodríguez, Mónica Gracia Villar

и другие.

Online Journal of Communication and Media Technologies, Год журнала: 2024, Номер 14(2), С. e202427 - e202427

Опубликована: Апрель 10, 2024

The current media ecosystem, marked by immediacy and social networks dynamics, has created a fertile field for disinformation. Faced with its exponential growth, since 2014, research focused on combating false content in the media. From descriptive approach, this study analyzed 200 documents fact-checking fake news published between 2014 2022 scientific journals indexed Scopus. This found that Europe United States are leading way number of authors publishing subject. universities ones host most significant working fact-checking, while methodologies used, mostly <i>ad hoc</i> due to novelty topic, allow reflect need promote work design, testing, evaluation prototypes or real experiences within field. common contributions include typologies manipulation mechanisms, models evaluating detecting disinformation, proposals combat strengthen verification studies role spread efforts develop literacy among public journalists, case fact-checkers, identification factors influence belief news, analysis relationship verification, politics, democracy. It is concluded it essential connects academy industry raise awareness address these issues different actors scenario.

Язык: Английский

Процитировано

5
Liars know they are lying: differentiating disinformation from disagreement DOI Creative Commons
Stephan Lewandowsky, Ullrich K. H. Ecker, John Cook

и другие.

Humanities and Social Sciences Communications, Год журнала: 2024, Номер 11(1)

Опубликована: Июль 31, 2024

Abstract Mis- and disinformation pose substantial societal challenges, have thus become the focus of a substantive field research. However, misinformation research has recently come under scrutiny on two fronts. First, political response emerged, claiming that aims to censor conservative voices. Second, some scholars questioned utility altogether, arguing is not sufficiently identifiable or widespread warrant much concern action. Here, we rebut these claims. We contend spread misinformation—and in particular willful disinformation—is demonstrably harmful public health, evidence-informed policymaking, democratic processes. also show outright lies can often be identified differ from good-faith contestation. conclude by showing how at least partially mitigated using variety empirically validated, rights-preserving methods do involve censorship.

Язык: Английский

Процитировано

5