Belittling the Source: Trustworthiness Indicators to Obfuscate Fake News on the Web

Esteves, Diego; Reddy, Aniketh Janardhan; Chawla, Piyush; Lehmann, Jens

doi:10.18653/v1/w18-5508

Cited by 20 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed methodology does not rely on gazetteers, lookups and normalization and also does not implement any encoded rules. Due to the nature of the generated feature vectors, we argue the outcomes of this work are of high relevance not only for NER on social media, but also to related (e.g., entity linking [27]) and also other downstream tasks [13]. Our experiments show that this has a direct positive impact in CRF and Decision Trees-based models, and the potential to improve overall B-LSTMs performance when more training data is available.…”

Section: Introductionmentioning

confidence: 91%

HORUS-NER: A Multimodal Named Entity Recognition Framework for Noisy Data

Esteves¹,

Marcelino²,

Chawla

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Recent work based on DeepLearning presents state-of-the-art (SOTA) performance in the named entity recognition (NER) task. However, such models still have the performance drastically reduced in noisy data (e.g., social media, search engines), when compared to the formal domain (e.g., newswire). Thus, designing and exploring new methods and architectures is highly necessary to overcome current challenges. In this paper, we shift the focus of existing solutions to an entirely different perspective. We investigate the potential of embedding word-level features extracted from images and news. We performed a very comprehensive study in order to validate the hypothesis that images and news (obtained from an external source) may boost the task on noisy data, revealing very interesting findings. When our proposed architecture is used: (1) We beat SOTA in precision with simple CRFs models (2) The overall performance of decision trees-based models can be drastically improved. (3) Our approach overcomes off-the-shelf models for this task. (4) Images and text consistently increased recall over different datasets for SOTA, but at cost of precision. All experiment configurations, data and models are publicly available to the research community at horus-ner.org

show abstract

Section: Introductionmentioning

confidence: 91%

HORUS-NER: A Multimodal Named Entity Recognition Framework for Noisy Data

Esteves¹,

Marcelino²,

Chawla

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Lastly, the credibility of user-profiles [16,37] and source websites [8,10,17,20] are also strong extrinsic features for determining truthfulness at an early stage [19]. To detect rumors and fake news on social media, Yuan et al [37] used user credibility as weak signals in their graph-based neural network model.…”

Section: Extrinsic Features For Determining Truthfulness Of Claimsmentioning

confidence: 99%

“…6 https://www.politifact.com/. 7 https://archive.org/details/simplewiki-20190201 8. https://github.com/attardi/wikiextractor.…”

mentioning

confidence: 99%

ECOL: Early Detection of COVID Lies Using Content, Prior Knowledge and Source Information

Baris

Boukhers

2021

Combating Online Hostile Posts in Regional Languages During Emergency Situation

View full text Add to dashboard Cite

Social media platforms are vulnerable to fake news dissemination, which causes negative consequences such as panic and wrong medication in the healthcare domain. Therefore, it is important to automatically detect fake news in an early stage before they get widely spread. This paper analyzes the impact of incorporating content information, prior knowledge, and credibility of sources into models for the early detection of fake news. We propose a framework modeling those features by using BERT language model and external sources, namely Simple English Wikipedia and source reliability tags. The conducted experiments on CONSTRAINT datasets demonstrated the benefit of integrating these features for the early detection of fake news in the healthcare domain.

show abstract

“…The work of Esteves et al (2018) provides a method of assessing the credibility of news sites by applying various machine learning methods to indicators, such as the article text content (e.g. text category, outbound links, contact information, or readability metrics) and the article metadata (e.g.…”

Section: Source Credibilitymentioning

confidence: 99%