1,701 research outputs found
Overview of the 8th Author Profiling Task at PAN 2020: Profiling Fake News Spreaders on Twitter
No full text[EN] This overview presents the Author Profiling shared task at
PAN 2020. The focus of this year's task is on determining whether or not
the author of a Twitter feed is keen to spread fake news. Two have been
the main aims: (i) to show the feasibility of automatically identifying
potential fake news spreaders in Twitter; and (ii) to show the difficulty
of identifying them when they do not limit themselves to just retweet
domain-specific news. For this purpose a corpus with Twitter data has
been provided, covering the English and Spanish languages. Altogether,
the approaches of 66 participants have been evaluated.First of all we thank the participants: 66 this year, record in terms of participants at PAN Lab since 2009! We have to thank also Martin Potthast, Matti
Wiegmann, and Nikolay Kolyada to help with the 66 Virtual Machines in the
TIRA platform. We thank Symanto for sponsoring the ex aequo award for the two best performing systems at the author profiling shared task of this year. The
work of Paolo Rosso was partially funded by the Spanish MICINN under the
research project MISMIS-FAKEnHATE on Misinformation and Miscommunication in social media: FAKE news and HATE speech (PGC2018-096212-B-C31).
The work of Anastasia Giachanou is supported by the SNSF Early Postdoc
Mobility grant under the project Early Fake News Detection on Social Media,
Switzerland (P2TIP2 181441).Rangel, F.; Giachanou, A.; Ghanem, BHH.; Rosso, P. (2020). Overview of the 8th Author Profiling Task at PAN 2020: Profiling Fake News Spreaders on Twitter. CEUR Workshop Proceedings. 2696:1-18. https://riunet.upv.es/handle/10251/166528S118269
Exploring Author Profiling for Fake News Detection
No full textThe proliferation of online media allows for the rapid dissemination of unmoderated news, unfortunately including fake news. The extensive spread of fake news poses a potent threat to both individuals and society. This paper focuses on designing author profiles to detect authors who are primarily engaged in publishing fake news articles. We build on the hypothesis that authors who write fake news repeatedly write only fake news articles, at least in short-term periods. Fake news authors have a distinct writing style compared to real news authors, who naturally want to maintain trustworthiness. We explore the potential to detect fake news authors by designing authors’ profiles based on writing style, sentiment, and co-authorship patterns. We evaluate our approach using a publicly available dataset with over 5000 authors and 20000 articles. For our evaluation, we build and compare different classes of supervised machine learning models. We find that the K-NN model performed the best, and it could detect authors who are prone to writing fake news with an 83% true positive rate with only a 5% false positive rate.</div
Improved fake mode free plane wave expansion method
No full textWe analyze the origin of the fake modes introduced by the plane wave expansion method with three-dimension (3D) supercell approximation. Through the detailed analysis of the energy distribution of fake modes and real modes, we propose the plane wave expansion-three planar-slab waveguides method to remove the fake modes and obtain the fake mode free band structure of a two-dimensional air hole photonic crystal slab. To the best of our knowledge, this is the first time that such a fake mode free photonic crystal band structure is presented. Our method is also definitely useful in designing other 3D devices. (C) 2011 Optical Society of Americ
Influence of liquid CO2 phase transition blasting on hydraulic fracturing in combined fracturing conditions
No full textFake News Detection
No full textThis paper examines the phenomenon known as fake news, how fast it spreads through new digital channels, and how this impact democracy. The paper sets out to construct a machine learning model, which can ultimately detect and classify articles as being either fake or real. Furthermore, the paper uses and examines different metrics that can evaluate the constructed model, and evaluates the model based on several metrics. We construct multiple models and compare them to each other. Additionally, different techniques for improving recurrent neural networks are explored. Ultimately the paper finds that it is possible to construct a model with nearly perfect accuracy. This entails that we suggest that machine learning models should be used on large social platforms to warn users that content might be fake news
Understanding Individual Differences in Faking: The Role of Ability to Fake and Motivation to Fake
No full textResearch on applicant faking has indicated that faking on personality tests may deteriorate the quality of hiring decisions and affect the validity of personality tests. In order to understand the occurrence of faking, scholars have attempted to explore the psychological process of applicant faking. The general idea is that the ability to fake and the motivation to fake should be two important antecedents of faking. In the current study, the ability to fake is operationally defined as the ability to identify the dimensions being measured in a personality test (i.e., ability to identify criteria (ATIC)). The motivation to fake (i.e., applicant test-taking motivation) is defined based on Valence, Instrumentality and Expectancy (VIE) theory.
Study 1 was conducted to explore the nomological framework of ATIC in personality tests, as well as the role of the frame-of-reference on the nature of ATIC ratings. Study 1 found that: (a) ATIC ratings in personality tests were related to verbal, numerical and abstract reasoning ability, but not associated with the construct of self-monitoring; (b) the frame-of-reference had an impact on the ATIC scores such that ATIC scores were higher in a specific personality measure than in a general big five measure; and (c) ATIC ratings across two personality measures also yielded an apparent pattern of cross-measure consistency. Study 2 was conducted to examine the role of the ability to fake and the motivation to fake on faking behavior and the criterion-related validity of personality scores. Results showed that (a) ATIC was not a predictor of faking and it worked to increase the predictive validity of personality scores; whereas (b) the motivation to fake was a predictor of faking and it suppressed the predictive validity of personality scores on GPA. The contributions, practical implications, and future research directions were discussed
Understanding fake news during the Covid-19 health crisis from the perspective of information behaviour: The case of Spain
No full textThe health crisis brought about by Covid-19 has generated a heightened need for information as a response to a situation of uncertainty and high emotional load, in which fake news and other informative content have grown dramatically. The aim of this work is to delve into the understanding of fake news from the perspective of information behaviour by analysing a sample of fake news items that were spread in Spain during the Covid-19 health crisis. A sample of 242 fake news items was collected from the Maldita.es website and analysed according to the criteria of cognitive and affective authority, interactivity, themes and potential danger. The results point to a practical absence of indicators of cognitive authority (53.7%), while the affective authority of these news items is built through mechanisms of discrediting people, ideas or movements (40.7%) and, secondarily, the use of offensive or coarse language (17.7%) and comparison or reference to additional information sources (26.6%). Interactivity features allow commenting in 24.3% of the cases. The dominant theme is society (43.1%), followed by politics (26.4%) and science (23.6%). Finally, fake news, for the most part, does not seem to pose any danger to the health or safety of people – the harm it causes is intangible and moral. The author concludes by highlighting the importance of a culture of civic values to combat fake news.Depto. de Biblioteconomía y DocumentaciónFac. de Ciencias de la DocumentaciónTRUEpu
How far does fake news influence public opinion?
No full text‘News’ is published and circulated in the physical and online world, meaning that it is no longer just the prerogative of monolithic corporations such as Fox News and the BBC; it can now be created by anyone across the globe with access to the world wide web, and cannot be authenticated or filtered by government or mainstream broadcasters as prerequisite to publication. ‘Fake news’ is one result of this pattern. The aim of my research is to demonstrate that modern ‘fake news’ has altered the electorate's relationship to current affairs, and has affected the democratic process by fabricating erroneous data and disseminating substandard political journalism. I will undertake this research as fake news is a development that is undoubtedly still relevant, and its effect on seismic events such as Brexit and the 2016 US Presidental Election is still being contended. Therefore, its influence needs to be scrutinized by a student like myself who is studying historical and contemporary publishing practices. The outcome of my independent study, which will take the form of a 6000-word academic essay, will be to elucidate the effect that fake news has on western politics, by collating and examining the work of journalists and thinkers, such as Matthew D’Ancona and James Ball, writing in a ‘post-truth’ age. Therefore, the significance of my work will be a dissection of the role ‘fake news’ now plays in the media market, whether for good or ill
The Art of Fake
No full textABSTRACT: It was Plato who defined the meaning and metaphysical value of Beauty in a way which was valid for all types of Arts, emphasizing on the concept of “Mimesis”. This aesthetic principle, developed mainly during ancient times, states that art represents an imitation of the real world. If criminal expertise of hand-writing has as its subject the study of handwriting based on scientific evidence regarding the graphics skills with the aim of identifying the author, can we consider counterfeiting of historical evidence as a form of art? Both in the case of hand-writing and works of art, there occur anatomo-physiological and psychological peculiarities specific to their author, the complex conditioned reflexes, and the dynamic stereotype which define a certain individual. Thus, the author of the fake needs to have the ability and training to accurately render the characteristics of the original.
KEYWORDS: art, fake, imitation, hand-writing, peculiaritie
Supervised classification methods for fake news identification
No full textAlong with the rapid increase in the popularity of online media, the proliferation of fake news and its propagation is also rising. Fake news can propagate with an uncontrollable speed without verification and can cause severe damages. Various machine learning and deep learning approaches have been attempted to classify the real and the false news. In this research, the author group presents a comprehensive performance evaluation of eleven supervised algorithms on three datasets for fake news classification. © 2020, Springer Nature Switzerland AG
- …
