An Explainable Fake News Detector Based on Named Entity Recognition and Stance Classification Applied to COVID-19

Magistris, Giorgio De; Russo, Samuele; Roma, Paolo; Starczewski, Janusz T.; Napoli, Christian

doi:10.3390/info13030137

Cited by 22 publications

(11 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many factors have been associated with vaccine hesitancy, including previous negative experiences, education level, healthcare trust, political views, and perception about the importance of vaccination [7]. Regarding COVID-19 vaccines, additional factors may play an important role in vaccine hesitancy: firstly, the speed at which the different vaccines were developed and approved within less than one year, while vaccine development commonly takes years to undergo preclinical stages and clinical trials; secondly, the durability of the immune response following the vaccination and its efficacy to limit the asymptomatic spread [17]; and thirdly, concern and uncertainty during the COVID-19 pandemic raised the spread of misinformation, which extended to affect COVID-19 vaccination [18].…”

Section: Discussionmentioning

confidence: 99%

Hesitancy toward the Full COVID-19 Vaccination among Kidney, Liver and Lung Transplant Recipients in Italy

et al. 2022

View full text Add to dashboard Cite

Background: Coronavirus disease 2019 (COVID-19) vaccination hesitancy is a threat as COVID-19 vaccines have reduced both viral transmission and virus-associated mortality rates, particularly in high-risk subgroups. Solid organ transplant recipients (SOTRs) are particularly vulnerable, as the underlying causes of their organ failure and the chronic immunosuppression are associated with a lower immune response to COVID-19 vaccines, and with an excessive risk of death due to SARS-CoV-2 infection. We aimed to evaluate COVID-19 vaccination hesitancy and its reasons in a population of SOTRs. Methods: All the SOTRs attending our post-transplant clinics were asked to fill in a vaccination status form with specific validated questions related to their willingness to receive a third vaccine dose. In the case of negative answers, the patients were encouraged to explain the reasons for their refusal. Among the SOTRs (1899), 1019 were investigated (53.7%). Results: Overall, 5.01% (51/1019) of the SOTRs raised concerns regarding the future third dose vaccination. In more detail, hesitancy rates were 3.3% (15/453), 4.2% (7/166), and 7.3% (29/400) among the investigated liver, lung, and kidney transplant recipients, respectively (p = 0.0018). The main reasons for hesitancy were fear of adverse events (30/51, 58.8%) and perceived lack of efficacy (21/51, 41.2%). Conclusions: Full adherence to ongoing or future vaccination campaigns is crucial to prevent, or at least reduce, COVID-19-related morbidity and mortality in fragile patients. The identification of the reasons influencing COVID-19 vaccination hesitancy in these patients is very important to establish appropriate and targeted patient–doctor communication strategies, and to further implement specific vaccination campaigns.

show abstract

Section: Discussionmentioning

confidence: 99%

Hesitancy toward the Full COVID-19 Vaccination among Kidney, Liver and Lung Transplant Recipients in Italy

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The best performance is observed using LSVM which obtains 0.9411 accuracy while LSTM provides an accuracy of 0.92. The third study does not perform fake news detection, rather it focuses on finding the class and subclass similarity of various articles/ news and provide the similarity score [66]. The current study, however, provides better performance concerning the accuracy and superior performance concerning precision, recall, and F1 score than existing studies.…”

Section: Results Of K-fold Cross-validationmentioning

confidence: 83%

Selective Feature Sets Based Fake News Detection for COVID-19 to Manage Infodemic

et al. 2022

View full text Add to dashboard Cite

During the COVID-19 pandemic, the spread of fake news became easy due to the wide use of social media platforms. Considering the problematic consequences of fake news, efforts have been made for the timely detection of fake news using machine learning and deep learning models. Such works focus on model optimization and feature engineering and the extraction part is under-explored area. Therefore, the primary objective of this study is to investigate the impact of features to obtain high performance. For this purpose, this study analyzes the impact of different subset feature selection techniques on the performance of models for fake news detection. Principal component analysis and Chi-square are investigated for feature selection using machine learning and pre-trained deep learning models. Additionally, the influence of different preprocessing steps is also analyzed regarding fake news detection. Results obtained from comprehensive experiments reveal that the extra tree classifier outperforms with a 0.9474 accuracy when trained on the combination of term frequency-inverse document frequency and bag of words features. Models tend to yield poor results if no preprocessing or partial processing is carried out. Convolutional neural network, long short term memory network, residual neural network (ResNet), and InceptionV3 show marginally lower performance than the extra tree classifier. Results reveal that using subset features also helps to achieve robustness for machine learning models.

show abstract

“…Social media and news articles are excellent sources for this type of research, and some datasets are even open access [14][15][16]. The study of these materials has strongly contributed to the identification of fake news [17][18][19][20][21][22][23][24][25][26][27][28], thus providing a basis for management decisions by government and business.…”

Section: Related Workmentioning

confidence: 99%

“…At the beginning of 2020, health concerns seemed of primary importance in the public media due to the COVID-19 outbreak. At that time, the enormous economic and social impact of COVID- 19 was not yet foreseeable, but only became apparent later. We observe that by week 12, mid-March 2020, the media tended to be "attracted" to new cases of COVID-19 (even though relatively few new cases have been reported), inadvertently ignoring the potential economic impact of the virus.…”

Section: Time Pattern Of the Covid-19 Topicsmentioning

confidence: 99%

See 1 more Smart Citation

Agenda-Setting for COVID-19: A Study of Large-Scale Economic News Coverage Using Natural Language Processing

Businger

Dollfus

et al. 2022

Int J Data Sci Anal

View full text Add to dashboard Cite

Over the past two years, organizations and businesses have been forced to constantly adapt and develop effective responses to the challenges of the COVID-19 pandemic. The acuteness, global scale and intense dynamism of the situation make online news and information even more important for making informed management and policy decisions. This paper focuses on the economic impact of the COVID-19 pandemic, using natural language processing (NLP) techniques to examine the news media as the main source of information and agenda-setters of public discourse over an eight-month period. The aim of this study is to understand which economic topics news media focused on alongside the dominant health coverage, which topics did not surface, and how these topics influenced each other and evolved over time and space. To this end, we used an extensive open-source dataset of over 350,000 media articles on non-medical aspects of COVID-19 retrieved from over 60 top-tier business blogs and news sites. We referred to the World Economic Forum’s Strategic Intelligence taxonomy to categorize the articles into a variety of topics. In doing so, we found that in the early days of COVID-19, the news media focused predominantly on reporting new cases, which tended to overshadow other topics, such as the economic impact of the virus. Different independent news sources reported on the same topics, showing a herd behavior of the news media during this global health crisis. However, a temporal analysis of news distribution in relation to its geographic focus showed that the rise in COVID-19 cases was associated with an increase in media coverage of relevant socio-economic topics. This research helps prepare for the prevention of social and economic crises when decision-makers closely monitor news coverage of viruses and related topics in other parts of the world. Thus, monitoring the news landscape on a global scale can support decision-making in social and economic crises. Our analyses point to ways in which this monitoring and issues management can be improved to remain alert to social dynamics and market changes.

show abstract

An Explainable Fake News Detector Based on Named Entity Recognition and Stance Classification Applied to COVID-19

Cited by 22 publications

References 29 publications

Hesitancy toward the Full COVID-19 Vaccination among Kidney, Liver and Lung Transplant Recipients in Italy

Hesitancy toward the Full COVID-19 Vaccination among Kidney, Liver and Lung Transplant Recipients in Italy

Selective Feature Sets Based Fake News Detection for COVID-19 to Manage Infodemic

Agenda-Setting for COVID-19: A Study of Large-Scale Economic News Coverage Using Natural Language Processing

Contact Info

Product

Resources

About