scholarly journals Transfer learning and GRU-CRF augmentation for COVID-19 fake news detection

Author(s):  
Andrea Karnyoto ◽  
Chengjie Sun ◽  
Bingquan Liu ◽  
Xiaolong Wang

The spread of fake news on online media is very dangerous and can lead to casualties, effects on psychology, character assassination, elections for political parties, and state chaos. Fake news that concerning Covid-19 massively spread during the pandemic. Detecting misinformation on the Internet is an essential and challenging task since humans face difficulty detecting fake news. We applied BERT and GPT2 as pre-trained using the BiGRU-Att-CapsuleNet model and BiGRU-CRF features augmentation to solve Fake News detection in Constraint @ AAAI2021 - COVID19 Fake News Detection in English Dataset. This research proved that our hybrid model with augmentation got better accuracy compared to our baseline model. It also showed that BERT gave a better result than GPT2 in all models; the highest accuracy we achieved for BERT is 0.9196, and GPT2 is 0.8986.

The purpose of this study is to analyze the formation of a media consumption culture in the information-rich multiconfessional and bilingual region of the Russian Federation – the Republic of Tatarstan. The authors of this article conducted a survey of 200 respondents aged 19-55 who are active users of the RuNet. The survey was carried out among students of the Kazan State Institute of Culture and Kazan Federal University, as well as media professionals from the Republic of Tatarstan. The anonymous survey was conducted in January-March 2019. Of all the respondents participated in this survey, 56% were aged 19-20. Eighty-three percent of the respondents were female – students, teachers and media workers of the Republic of Tatarstan. Sixty-five percent of them combined their education with work. Ninety-eight percent of the respondents received information from the Internet, 76% watched information programs on television, 27% listened to the radio and only 7.5% of the respondents still read newspapers. Sixty-eight percent of the surveyed trusted messages received from news agencies, while 78% trusted news messages received from news aggregators. Ninety percent of the respondents trusted information received from online media; 11% trusted the information received from social networks and only 4.5% of the respondents trusted the information discussed in blogs. The high percentage of trust to information obtained from the media and the low percentage of trust to information obtained from blogs indicates the current culture of media use and media literacy of the population in the situation with fake news. Of all the respondents answering the question "Do you refer to the source of information you use on the Internet?", 91.5% answered positively. Disturbingly, 92.5% of the surveyed believe that they do not have to pay for the information received from online media. The authors explain the refusal to pay for content with a small amount of exclusive and analytical materials in the information field of the Republic of Tatarstan


2019 ◽  
Vol 1 (1) ◽  
pp. 20
Author(s):  
Muh.Ulil S. Negara

Abstract— The background of this research is the increase of the distribution of fake news in cyberspace to coincide with the 2019 general election (Pemilu) campaign in Indonesia. Undergraduate students in Indonesia, most of whom are beginner voters in the 2019 election, are one of the most important campaign targets calculated by each political party. Fake news produced massively and structurally by political parties to get support from voters can break the unity and the harmony of the nation. Students as young people whose mindsets are critical and have idealism in fighting for their ideas must be able to distinguish between true and fake news for the safety of their own insights. The research method used is a quantitative method to understand the behavior of students in using mobile phones which is the fastest media for disseminating information through the internet. Understanding these behaviors will provide an overview of the impact of the application or information channel most often opened by someone to their ability to distinguish true and fake news. This study aims to get a strategy that needs to be done to improve student behavior in using mobile phones, which will affect the quality of information obtained from the internet via mobile phones. So that young person who are productive and have the right insight are not easily provoked by fake news from the internet


2022 ◽  
Vol 1 (1) ◽  
pp. 5-18
Author(s):  
Hana Pravdová ◽  
Miroclav Kapec

The study deals with the issue of misleading information in the Internet environment. The authors define and analyse basic terms denoting various methods of disinformation. They point to the fact that there are specific terms and phenomena forming the thematic axis of the current discourse on disinformation practices in online media. They state that there is quite a lot of chaos in the field of terminology. This is the reason why they critically reconsider the existing knowledge related to disinformation, such as fake news and the like. The ambition of the authors is the conceptualisation of disinformation methods in the context of a broadening of genres and social background. They emphasise the need to research the issue because the information quality of various blogs, posts, comments, etc. raises many unanswered questions or incorrect answers. In their analysis of the issue, they use the basic methods of logical analysis, the hermeneutic approach, as well as selectively chosen examples of individual typological variants of disinformation.


2018 ◽  
Vol 73 ◽  
pp. 14006
Author(s):  
Hedi Pudjo Santosa ◽  
Nurul Hasfi ◽  
Triyono Lukmantoro

In the internet era, a hoax is a real threat for democracy, as it spreads misleading and fake information that creats uncertain political communication. During the 2014 Indonesian presidential election, a hoax was rapidly spreading thorough social media. Morover, in Indonesian political context, a hoax construct strategically by using primordialism issue. This study uses critical discourse analysis to identify a pattern of hoax during the 2014 Indonesian presidential election, particularly to show how primordialism constructs an unequel society. The data was taken from political discussion among 8 influential Twitter accounts, two months before the election. The study found that 1) A hoax was produced by using many techniques; 2) Mainstream ‘online media’ involved in the production of the hoax, particularly by constructing sensational headline. Meanwhile, fake news commonly produced and distributed by pseudonym Twitter accounts; 3) Both hoax and fake news generally run under a mechanism of primordialism issue.


Author(s):  
Lena Nadarevic ◽  
Rolf Reber ◽  
Anne Josephine Helmecke ◽  
Dilara Köse

Abstract To better understand the spread of fake news in the Internet age, it is important to uncover the variables that influence the perceived truth of information. Although previous research identified several reliable predictors of truth judgments—such as source credibility, repeated information exposure, and presentation format—little is known about their simultaneous effects. In a series of four experiments, we investigated how the abovementioned factors jointly affect the perceived truth of statements (Experiments 1 and 2) and simulated social media postings (Experiments 3 and 4). Experiment 1 explored the role of source credibility (high vs. low vs. no source information) and presentation format (with vs. without a picture). In Experiments 2 and 3, we additionally manipulated repeated exposure (yes vs. no). Finally, Experiment 4 examined the role of source credibility (high vs. low) and type of repetition (congruent vs. incongruent vs. no repetition) in further detail. In sum, we found no effect of presentation format on truth judgments, but strong, additive effects of source credibility and repetition. Truth judgments were higher for information presented by credible sources than non-credible sources and information without sources. Moreover, congruent (i.e., verbatim) repetition increased perceived truth whereas semantically incongruent repetition decreased perceived truth, irrespectively of the source. Our findings show that people do not rely on a single judgment cue when evaluating a statement’s truth but take source credibility and their meta-cognitive feelings into account.


Libri ◽  
2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Jenna Kammer ◽  
Kodjo Atiso ◽  
Edward Mensah Borteye

Abstract This comparative cultural study examines differences in digital citizenship between undergraduate information literacy students at two different, but similar, universities across the globe from each other. Under the notion that the internet and prevalence of mobile devices allow students to participate online as digital citizens in ways that were impossible before, we use mixed methods to compare the attitudes and experiences of undergraduate students at a university in the midwestern United States (U.S.), with a university on the southwestern coast of Ghana. We also examine the policies related to technology use at these schools. The findings indicate that Ghanaian students had higher levels of digital citizenship. Other findings suggest that network issues are a problem for students in both schools, especially for Ghana, and ethical aspects of internet use, like cyberbullying, hacking, and fake news, deter students from participating online as much as they would like.


Designs ◽  
2021 ◽  
Vol 5 (3) ◽  
pp. 42
Author(s):  
Eric Lazarski ◽  
Mahmood Al-Khassaweneh ◽  
Cynthia Howard

In recent years, disinformation and “fake news” have been spreading throughout the internet at rates never seen before. This has created the need for fact-checking organizations, groups that seek out claims and comment on their veracity, to spawn worldwide to stem the tide of misinformation. However, even with the many human-powered fact-checking organizations that are currently in operation, disinformation continues to run rampant throughout the Web, and the existing organizations are unable to keep up. This paper discusses in detail recent advances in computer science to use natural language processing to automate fact checking. It follows the entire process of automated fact checking using natural language processing, from detecting claims to fact checking to outputting results. In summary, automated fact checking works well in some cases, though generalized fact checking still needs improvement prior to widespread use.


2021 ◽  
Author(s):  
Svitlana Mazepa ◽  
Serhiy Banakh ◽  
Andriy Melnyk ◽  
Sergiy Pugach ◽  
Oleksandra Yavorska ◽  
...  

2020 ◽  
Vol 5 (7) ◽  
pp. 431
Author(s):  
Okfida Yani Syaf

Students nowadays interact more frequently through the internet using English. As an international language, English is used by most internet users, both by application companies and social networks, as well as by users. Internet usage can be more easily obtained, especially in big cities. This affects the students’ way of thinking, learning and behaving because they can learn everything easily and quickly through online media available at the internet. The aim of this research is to show the effect of internet use habit on English achievement for class VIII students at SMPI Al Azhar 8 in Bekasi. This research based on survey methods using technical correlational analysis. While the data and information were obtained by a questionnaire. The sample is taken with purposive sampling technique that is 44 students. Based on the results of the study, it can be concluded that: There is a significant effect of the habit of interacting through the internet on the English achievement. This is evidenced by the acquisition of the results of the Sig. 0,000 <0,05dan t value = 4,365 which means there is a significant effect.


Sign in / Sign up

Export Citation Format

Share Document