Twitter rumour detection in the health domain

Abstract

DOI to the publisher's website.• The final author version and the galley proof are versions of the publication after peer review.• The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User Agreement:

How the Health Rumor Misleads People’s Perception in a Public Health Emergency: Lessons from a Purchase Craze during the COVID-19 Outbreak in China

“…Academics have reached a consensus that the study of rumors associated with public health contributes to the sociology, management, and communication science of health by enhancing our understanding of lay health knowledge and beliefs, as well as the situated basis of health-relevant actions. Academics also recommend some communication methods for tackling and correcting health rumors [ 4 , 9 , 10 , 11 , 12 , 13 , 14 ]. However, in order to keep people from believing these rumors, it is crucial to apply effective health communication to eliminate these rumors during a public health emergency as ex ante prevention instead of as an ex post response.…”

A New Application of Social Impact in Social Media for Overcoming Fake News in Health

“…Most of them are based on data-based models, i.e., they use automatic learning techniques to identify misinformation. Based on these techniques, different applications have been developed with different objectives and in different contexts, such as detecting opinion spam on review sites, detecting false news and spam in microblogging, and assessing the credibility of online health information [6,42,43]. These techniques include both human intervention and algorithms to verify the veracity of information across technologies, such as artificial intelligence (AI) and natural language processing (NLP) [44].…”

Rumour Detection Models & Tools for Social Networking Sites

“…Hence, the old rumour words (i.e., dataset) are obsolete when compared with emerging rumour words. These dataset are again categorized based on domains, obtaining dataset in specific domain and judging rumour and non-rumour posts is limited to certain extent, but collectively testing with multiple domains and comparing with each of the respective domain resulted in ambiguity outputs [3]. Many of architectures make use of Machine learning technique which is a time-consuming process that can be improvised with the use of pre-defined knowledge based rules guided with semantic ontology.…”

“…Detecting of short rumour tweets such as -Obama is a muslim guy‖, this does not require excessive learning for this authenticated books to be checked and a conclusion can be derived within seconds using a pre-defined rule based classifier [13]. In literature, most of the researchers had picked datasets of their own considering a particular scenario and few have taken from previously existed rumour datasets [3] [13] [16]. Many of the researchers had picked rumour dataset of microblogs from Twitter, Facebook, Weibo and Instagram to predict the category of rumours [1] [18].…”

“…Twitter messaging application which is widely used by millions of people for posting, giving reply to specific tweets, forwarding of tweet to other users adversely influence on Health domains by creating mental tension in the society. To overcome, health domain problems from Twitter, few parameters are picked for evaluation such as statistics of users, sentiments of specific tweets, followers of root of tweet along with URLs and fed to classifiers for finding the rumours [3]. A new classification algorithm was proposed using statistical metrics for segregation of rumour and non-rumour twitter posts based on users frequency of interaction, structure & network establishment, temporary connectivity and linguistic features.…”