scholarly journals Detecting COVID-19-Related Fake News Using Feature Extraction

2022 ◽  
Vol 9 ◽  
Author(s):  
Suleman Khan ◽  
Saqib Hakak ◽  
N. Deepa ◽  
B. Prabadevi ◽  
Kapal Dev ◽  
...  
Keyword(s):  
Social Media ◽  
State Of The Art ◽  
Electronic Media ◽  
Random Forest Classifier ◽  
Machine Learning Algorithms ◽  
Digital Marketing ◽  
Fake News ◽  
Text Data ◽  
News Sources ◽  
Computational Overhead

Since its emergence in December 2019, there have been numerous posts and news regarding the COVID-19 pandemic in social media, traditional print, and electronic media. These sources have information from both trusted and non-trusted medical sources. Furthermore, the news from these media are spread rapidly. Spreading a piece of deceptive information may lead to anxiety, unwanted exposure to medical remedies, tricks for digital marketing, and may lead to deadly factors. Therefore, a model for detecting fake news from the news pool is essential. In this work, the dataset which is a fusion of news related to COVID-19 that has been sourced from data from several social media and news sources is used for classification. In the first step, preprocessing is performed on the dataset to remove unwanted text, then tokenization is carried out to extract the tokens from the raw text data collected from various sources. Later, feature selection is performed to avoid the computational overhead incurred in processing all the features in the dataset. The linguistic and sentiment features are extracted for further processing. Finally, several state-of-the-art machine learning algorithms are trained to classify the COVID-19-related dataset. These algorithms are then evaluated using various metrics. The results show that the random forest classifier outperforms the other classifiers with an accuracy of 88.50%.

Fake It “Till You Make It”: Debunking Fake News in a Post-Truth America

2019 ◽  
Vol 8 (1) ◽  
pp. 114-133
Keyword(s):  
Social Media ◽  
First Amendment ◽  
Presidential Election ◽  
Political Discourse ◽  
Cutting Edge ◽  
American People ◽  
Fake News ◽  
News Sources ◽  
The Media ◽  
The U.S

Since the 2016 U.S. presidential election, attacks on the media have been relentless. “Fake news” has become a household term, and repeated attempts to break the trust between reporters and the American people have threatened the validity of the First Amendment to the U.S. Constitution. In this article, the authors trace the development of fake news and its impact on contemporary political discourse. They also outline cutting-edge pedagogies designed to assist students in critically evaluating the veracity of various news sources and social media sites.

scholarly journals Exploring Adversarial Attacks and Defences for Fake Twitter Account Detection

Technologies ◽  
2020 ◽  
Vol 8 (4) ◽  
pp. 64
Author(s):  
Panagiotis Kantartopoulos ◽  
Nikolaos Pitropakis ◽  
Alexios Mylonas ◽  
Nicolas Kylilis
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Test Phase ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Fake News ◽  
Specific Subject ◽  
Learning Techniques ◽  
Twitter Account

Social media has become very popular and important in people’s lives, as personal ideas, beliefs and opinions are expressed and shared through them. Unfortunately, social networks, and specifically Twitter, suffer from massive existence and perpetual creation of fake users. Their goal is to deceive other users employing various methods, or even create a stream of fake news and opinions in order to influence an idea upon a specific subject, thus impairing the platform’s integrity. As such, machine learning techniques have been widely used in social networks to address this type of threat by automatically identifying fake accounts. Nonetheless, threat actors update their arsenal and launch a range of sophisticated attacks to undermine this detection procedure, either during the training or test phase, rendering machine learning algorithms vulnerable to adversarial attacks. Our work examines the propagation of adversarial attacks in machine learning based detection for fake Twitter accounts, which is based on AdaBoost. Moreover, we propose and evaluate the use of k-NN as a countermeasure to remedy the effects of the adversarial attacks that we have implemented.

scholarly journals Fake News Detection on Social Media Using A Natural Language Inference Approach

2020 ◽  
Author(s):  
Amir Bidgoly ◽  
Hossein Amirkhani ◽  
Fariba Sadeghi
Keyword(s):  
Social Media ◽  
Natural Language ◽  
News Item ◽  
Support Vector ◽  
Statistical Features ◽  
Fake News ◽  
K Nearest Neighbors ◽  
News Sources ◽  
Online Social Media ◽  
Embedding Methods

Abstract Fake news detection is a challenging problem in online social media, with considerable social and political impacts. Several methods have already been proposed for the automatic detection of fake news, which are often based on the statistical features of the content or context of news. In this paper, we propose a novel fake news detection method based on Natural Language Inference (NLI) approach. Instead of using only statistical features of the content or context of the news, the proposed method exploits a human-like approach, which is based on inferring veracity using a set of reliable news. In this method, the related and similar news published in reputable news sources are used as auxiliary knowledge to infer the veracity of a given news item. We also collect and publish the first inference-based fake news detection dataset, called FNID, in two formats: the two-class version (FNID-FakeNewsNet) and the six-class version (FNID-LIAR). We use the NLI approach to boost several classical and deep machine learning models including Decision Tree, Naïve Bayes, Random Forest, Logistic Regression, k-Nearest Neighbors, Support Vector Machine, BiGRU, and BiLSTM along with different word embedding methods including Word2vec, GloVe, fastText, and BERT. The experiments show that the proposed method achieves 85.58% and 41.31% accuracies in the FNID-FakeNewsNet and FNID-LIAR datasets, respectively, which are 10.44% and 13.19% respective absolute improvements.

scholarly journals IMPLEMENTATION OF INNOVATIVE APPROACHES IN DIGITAL MARKETING

2021 ◽  
Author(s):  
Ihor Ponomarenko
Keyword(s):  
Social Media ◽  
Marketing Strategy ◽  
Data Science ◽  
Target Audience ◽  
Machine Learning Algorithms ◽  
Digital Marketing ◽  
Digital Environment ◽  
Innovative Products ◽  
Potential Customers ◽  
Innovative Approaches

The article focuses on the intense transformation of marketing in connection with the processes of digitalization and socio-economic transformations as a result of the COVID-19 pandemic. The features of using the main digital marketing tools as effective elements for establishing communications with the target audience are revealed. The expediency of introducing innovative approaches and technologies to increase the conversion rate has been proven. In the context of digital marketing, traffic generation involves the implementation of measures set that encourage potential customers to follow the company's links. The presence of an effective marketing strategy of the company in the digital environment involves the use of sales funnels, with the characteristics of the traffic involved at each stage. The focus of the company on generating organic and paid advertising traffic in accordance with the specifics of the company's functioning in the digital environment has been substantiated. The need for market research has been proven to create, on an ongoing basis, personalized content that will be in demand among the relevant groups of potential customers. It is not enough for modern subscribers to periodically provide access to thematic content, it is necessary to ensure the constant interest and desire of users to get acquainted with the materials, which is possible only with the implementation of flexible and original approaches. The necessity of using various digital marketing tools has been substantiated, since a large number of companies focus only on social media. The interest of large companies in creating specialized social media to promote specialized content increases competition and leads to the introduction of innovative products that can be used to increase the efficiency of formation and improvement of marketing strategies in the digital environment. The specificity of the machine learning algorithms application to improve the effectiveness of a company's marketing strategy in the digital environment is disclosed. Using a variety of data science approaches, it is possible to segment the target audience based on large amounts of data and increase the likelihood of increasing the level of potential customers loyalty.

scholarly journals Building a Dataset for Detecting Fake News in Amharic Language

2021 ◽  
pp. 76-83
Author(s):  
Tewodros Tazeze ◽  
Raghavendra R
Keyword(s):  
Social Media ◽  
Information Exchange ◽  
Detection System ◽  
Fake News ◽  
News Sources ◽  
Vernacular Language ◽  
Semitic Language ◽  
Media Platform ◽  
Tremendous Challenge ◽  
High Range

The rapid growth and expansion of social media platform has filled the gap of information exchange in the day to day life. Apparently, social media is the main arena for disseminating manipulated information in a high range and exponential rate. The fabrication of twisted information is not limited to ones language, society and domain, this is particularly observed in the ongoing COVID-19 pandemic situation. The creation and propagation of fabricated news creates an urgent demand for automatically classification and detecting such distorted news articles. Manually detecting fake news is a laborious and tiresome task and the dearth of annotated fake news dataset to automate fake news detection system is still a tremendous challenge for low-resourced Amharic language (after Arabic, the second largely spoken Semitic language group). In this study, Amharic fake news dataset are crafted from verified news sources and various social media pages and six different machine learning classifiers Naïve bays, SVM, Logistic Regression, SGD, Random Forest and Passive aggressive Classifier model are built. The experimental results show that Naïve bays and Passive Aggressive Classifier surpass the remaining models with accuracy above 96% and F1- score of 99%. The study has a significant contribution to turn down the rate of disinformation in vernacular language.

scholarly journals Towards Combating Pandemic-Related Misinformation in Social Media

2021 ◽  
pp. 140-158
Author(s):  
Isa Inuwa-Dutse
Keyword(s):  
Social Media ◽  
Public Discourse ◽  
Preventive Measures ◽  
State Of The Art ◽  
Fake News ◽  
Social Distancing ◽  
The Public ◽  
Toxic Impact ◽  
Online Social Media ◽  
Social Media Platforms

Conventional preventive measures during pandemics include social distancing and lockdown. Such measures in the time of social media brought about a new set of challenges – vulnerability to the toxic impact of online misinformation is high. A case in point is COVID-19. As the virus propagates, so does the associated misinformation and fake news about it leading to an infodemic. Since the outbreak, there has been a surge of studies investigating various aspects of the pandemic. Of interest to this chapter are studies centering on datasets from online social media platforms where the bulk of the public discourse happens. The main goal is to support the fight against negative infodemic by (1) contributing a diverse set of curated relevant datasets; (2) offering relevant areas to study using the datasets; and (3) demonstrating how relevant datasets, strategies, and state-of-the-art IT tools can be leveraged in managing the pandemic.

scholarly journals Peluang Revolusi Industri 4.0 Bidang Pemasaran: Pemanfaatan Aplikasi E-commerce, Sosial Media Instagram dan Digital Marketing terhadap keputusan Instant Online Buying Konsumen Generasi Millenial

2020 ◽  
Vol 3 (2) ◽  
pp. 86
Author(s):  
Bambang Setia Wibowo ◽  
Diaz Haryokusumo
Keyword(s):  
Social Media ◽  
Millennial Generation ◽  
Industrial Revolution ◽  
Online Shopping ◽  
Electronic Media ◽  
Positive Influence ◽  
Digital Marketing ◽  
Online Purchases ◽  
Online Buying ◽  
Positive Effect

<p><br />This study examined the influence of e-commerce application, social media instagram and digital marketing to online purchases of millennial generation consumers. Respondents of this study were 152 university students who have already shopped online at e-commerce applications, have ever seen e-commerce advertisements on electronic media and have used social media instagram for online shopping participated in this reseach. There are several findings in this study. First, e-commerce application has positive influence to online purchases of millennial generation consumers. Second, social media instagram has postive effect to online purchases of millennial generation consumers. Third, digital marketing has positive effect to online purchases of millennial generation consumers.<br />Keywords : industrial revolution 4.0, e-commerce, instagram, digital marketing, instant online buying, millennial generation consumers</p>

scholarly journals Will the crowd game the algorithm? Using layperson judgments to combat misinformation on social media by downranking distrusted sources

2019 ◽  
Author(s):  
Ziv Epstein ◽  
Gordon Pennycook ◽  
David Gertler Rand
Keyword(s):  
Social Media ◽  
Political Polarization ◽  
Survey Experiment ◽  
Fake News ◽  
News Sources ◽  
Ranking Algorithms ◽  
Social Media Platforms ◽  
Highly Correlated ◽  
High Level ◽  
Survey Responses

How can social media platforms fight the spread of misinformation? One possibility is to use newsfeed algorithms to downrank content from sources that users rate as untrustworthy. But will laypeople unable to identify misinformation sites due to motivated reasoning or lack of expertise? And will they “game” this crowdsourcing mechanism to promote content that aligns with their partisan agendas? We conducted a survey experiment in which N = 984 Americans indicated their trust in numerous news sites. Half of the participants were told that their survey responses would inform social media ranking algorithms - creating a potential incentive to misrepresent their beliefs. Participants trusted mainstream sources much more than hyper-partisan or fake news sources, and their ratings were highly correlated with professional fact-checker judgments. Critically, informing participants that their responses would influence ranking algorithms did not diminish this high level of discernment, despite slightly increasing the political polarization of trust ratings.

Cracking Open the News Feed

2021 ◽  
Vol 1 ◽  
Author(s):  
Andy Guess ◽  
Kevin Aslett ◽  
Joshua Tucker ◽  
Richard Bonneau ◽  
Jonathan Nagler
Keyword(s):  
Social Media ◽  
Fake News ◽  
Older Americans ◽  
News Sources ◽  
Older Users ◽  
Different Types ◽  
Supervised Classifiers ◽  
Sharing Patterns ◽  
First Time

In this study, we analyze for the first time newly available engagement data covering millions of web links shared on Facebook to describe how and by which categories of U.S. users different types of news are seen and shared on the platform. We focus on articles from low-credibility news publishers, credible news sources, purveyors of clickbait, and news specifically about politics, which we identify through a combination of curated lists and supervised classifiers. Our results support recent findings that more fake news is shared by older users and conservatives and that both viewing and sharing patterns suggest a preference for ideologically congenial misinformation. We also find that fake news articles related to politics are more popular among older Americans than other types, while the youngest users share relatively more articles with clickbait headlines. Across the platform, however, articles from credible news sources are shared over 5 times more often and viewed over 7 times more often than articles from low-credibility sources. These findings offer important context for researchers studying the spread and consumption of information — including misinformation — on social media.

Sign in / Sign up

Export Citation Format

Share Document