Toward Automated Fact-Checking

Hassan, Naeemul; Arslan, Fatma Taş; Li, Chengkai; Tremayne, Mark

doi:10.1145/3097983.3098131

Cited by 224 publications

(74 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Zubiaga et al [43] present a survey of approaches for rumor detection, including veracity classification and the collection and annotation of rumor-focused datasets from social media. Finally, a related problem is automated fact checking, which pertains to the classification of sentences into non-factual, unimportant factual and check-worthy factual statements [12]. Fact checking methods rely on structured knowledge from databases, such as FreeBase and DBpedia, which contain entities, events and their relations.…”

Section: Related Workmentioning

confidence: 99%

Detection and visualization of misleading content on Twitter

Boididou

Papadopoulos

Zampoglou

et al. 2017

Int J Multimed Info Retr

133

View full text Add to dashboard Cite

The problems of online misinformation and fake news have gained increasing prominence in an age where user-generated content and social media platforms are key forces in the shaping and diffusion of news stories. Unreliable information and misleading content are often posted and widely disseminated through popular social media platforms such as Twitter and Facebook. As a result, journalists and editors are in need of new tools that can help them speed up the verification process for content that is sourced from social media. Motivated by this need, in this paper we present a system that supports the automatic classification of multimedia Twitter posts into credible or misleading. The system leverages credibility-oriented features extracted from the tweet and the user who published it, and trains a two-step classification model based on a novel semisupervised learning scheme. The latter uses the agreement between two independent pre-trained models on new posts as guiding signals for retraining the classification model. We analyze a large labeled dataset of tweets that shared debunked fake and confirmed real images and videos, and show that integrating the newly proposed features, and making use of bagging in the initial classifiers and of the semi-supervised learning scheme, significantly improves classification accuracy. Moreover, we present a web-based application for visualizing and communicating the classification results to end users.

show abstract

Section: Related Workmentioning

confidence: 99%

Detection and visualization of misleading content on Twitter

Boididou

Papadopoulos

Zampoglou

et al. 2017

Int J Multimed Info Retr

133

View full text Add to dashboard Cite

show abstract

“…Potentially the most impactful application of technocognition is the "holy grail of fact-checking"computer-assisted detection and assessment of the veracity of misinformation (Hassan et al, 2015). There have been a number of attempts to automatically detect misinformation using a variety of algorithms with varying degrees of success.…”

Section: Technocognitionmentioning

confidence: 99%

Understanding and Countering Misinformation About Climate Change

Cook

2019

Advances in Media, Entertainment, and the Arts

View full text Add to dashboard Cite

While there is overwhelming scientific agreement on climate change, the public has become polarized over fundamental questions such as human-caused global warming. Communication strategies to reduce polarization rarely address the underlying cause: ideologically-driven misinformation. In order to effectively counter misinformation campaigns, scientists, communicators, and educators need to understand the arguments and techniques in climate science denial, as well as adopt evidence-based approaches to neutralizing misinforming content. This chapter reviews analyses of climate misinformation, outlining a range of denialist arguments and fallacies. Identifying and deconstructing these different types of arguments is necessary to design appropriate interventions that effectively neutralize the misinformation. This chapter also reviews research into how to counter misinformation using communication interventions such as inoculation, educational approaches such as misconception-based learning, and the interdisciplinary combination of technology and psychology known as technocognition.

show abstract

“…Fact identification approaches, especially for news related sources, try to classify sentences into nonfactual, unimportant factual and 'check worthy' factual statements [11] so they can be filtered prior to fact extraction. Fact extraction is a type of information extraction (IE) problem that runs alongside information extraction techniques for concepts such as event, topic, location and time.…”

Section: Eyewitness Media and Fact Extractionmentioning

confidence: 99%

Social Computing for Verifying Social Media Content in Breaking News

Middleton

Papadopoulos

Kompatsiaris

2018

IEEE Internet Comput.

View full text Add to dashboard Cite

(max 150) Social media is the place to go for both journalists and the general public when news events break, offering a real-time source of eyewitness images and videos through platforms like YouTube, Instagram, and Periscope. Yet, the value of such content as a means of documenting and disseminating breaking news is compromised by the increasing amount of content misuse and false claims in social media. To this end, cost-effective social computing solutions for user-generated content verification are crucial for retaining the value and trust in social media for breaking news. KeywordsSocial Media; Multimedia; Multimedia Forensics; Natural Language Processing; Information Extraction; Fact Checking; Geoparsing; Verification; News ACM Taxonomy H.5.1 Multimedia Information Systems; I.2.7 Natural Language Processing; I.2.6.g Machine learningMost people have a smartphone in their pocket today, so eyewitnesses experiencing an event like a terror attack will often post real-time claims, such as the numbers dead or injured in a location, to Twitter or Facebook. Eyewitness images and videos will also be uploaded to sites like YouTube and Instagram, or even streamed live to sites like Periscope. For events such as the Paris shootings 2015 [1] the first eyewitness videos of the various shootings were posted within 5-10 minutes of the event happening. This was followed about 20-30 minutes later with verified news reports from sources such as Le Figaro, BBC and CNN. In other cases, verifying eyewitness or user-generated media and claims can take much longer, from hours to even days, as for instance in the case of the Malaysia Airlines Flight 17 shot down on 17 July 2014. In many cases as soon as a breaking news event starts trending on Twitter, it is accompanied by considerable amounts of false claims and content misuse [2]. This involves the use of multimedia for misinforming the public and misrepresenting people, organizations and events. Misuse practices range from publishing content that has been digitally tampered using photo-editing software to falsely associating content with an unfolding event. Figure 1 illustrates three recent real-world examples of content misuse that quickly reached wide audiences, while the survey in [2] contains an extensive discussion on the problem of rumour detection in social media.(a) (b) (c) Figure 1 Given the grave societal and economic impact of having misused content and false claims featured in mainstream news, it becomes extremely important for news organizations to be able to verify eyewitness media in very short time. To this end, journalists are turning to social computing approaches to automatically analyse and verify [3] user generated content (UGC) in real time. The eventual hope is that cost-effective social computing can reduce the time spent on verification to timescales nearer to real time. Social Multimedia Forensics and Supervised VerificationMethods from the field of digital forensics are often used for assessing the veracity of multimedia items (images/videos...

show abstract

Toward Automated Fact-Checking

Cited by 224 publications

References 19 publications

Detection and visualization of misleading content on Twitter

Detection and visualization of misleading content on Twitter

Understanding and Countering Misinformation About Climate Change

Social Computing for Verifying Social Media Content in Breaking News

Contact Info

Product

Resources

About