Characterization of Fake News Based on Subjectivity Lexicons

2020 ◽  
Vol 1 (4) ◽  
pp. 419-441
Author(s):  
Caio L.M. Jeronimo ◽  
Leandro B. Marinho ◽  
Cclaudio E.C. Carmpelo ◽  
Adriano Veloso ◽  
Allan S. Da Costa Melo
Keyword(s):  
Social Networks ◽  
Brazilian Portuguese ◽  
News Article ◽  
Bag Of Words ◽  
Fake News ◽  
Feature Vectors ◽  
Textual Content

While many works investigate spread patterns of fake news in social networks, we focus on the textual content. Instead of relying on syntactic representations of documents (aka Bag of Words) as many works do, we seek more robust representations that may better differentiate fake from legitimate news. We propose to consider the subjectivity of news under the assumption that the subjectivity levels of legitimate and fake news are significantly different. For computing the subjectivity level of news, we rely on a set subjectivity lexicons for both Brazilian Portuguese and English languages. We then build subjectivity feature vectors for each news article by calculating the Word Mover's Distance (WMD) between the news and these lexicons considering the embedding the news words lie in, in order to analyze and classify the documents. The results demonstrate that our method is robust, especially in scenarios where training and test domains are different.

scholarly journals CNMF: A Community-Based Fake News Mitigation Framework

Information ◽  
2021 ◽  
Vol 12 (9) ◽  
pp. 376
Author(s):  
Shaimaa Galal ◽  
Noha Nagy ◽  
Mohamed. E. El-Sharkawi
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
User Behavior ◽  
News Article ◽  
Fake News ◽  
Community Based ◽  
The Social ◽  
Mitigation Techniques ◽  
Directing Attention ◽  
Entire Network

Fake news propagation in online social networks (OSN) is one of the critical societal threats nowadays directing attention to fake news mitigation and intervention techniques. One of the typical mitigation techniques focus on initiating news mitigation campaigns targeting a specific set of users when the infected set of users is known or targeting the entire network when the infected set of users is unknown. The contemporary mitigation techniques assume the campaign users’ acceptance to share a mitigation news (MN); however, in reality, user behavior is different. This paper focuses on devising a generic mitigation framework, where the social crowd can be employed to combat the influence of fake news in OSNs when the infected set of users is undefined. The framework is composed of three major phases: facts discovery, facts searching and, community recommendation. Mitigation news circulation is accomplished by recruiting a set of social crowd users (news propagators) who are likely to accept posting the mitigation news article. We propose a set of features that identify prospect OSN audiences and news propagators. Moreover, we inspect the variant properties of the news circulation process, such as incentivizing news propagators, determining the required number of news propagators, and the adaptivity of the MN circulation process. The paper pinpoints the significance of facts searching and news propagator’s behavior features introduced in the experimental results.

Extreme Gradient Boosting for Cyberpropaganda Detection

2021 ◽  
Author(s):  
Jaouhar Fattahi ◽  
Mohamed Mejri ◽  
Marwa Ziadia
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Gradient Boosting ◽  
The Internet ◽  
Bag Of Words ◽  
Fake News ◽  
Inverse Document Frequency ◽  
Document Frequency ◽  
Extreme Gradient Boosting ◽  
New Phenomena

Propaganda, defamation, abuse, insults, disinformation and fake news are not new phenomena and have been around for several decades. However, with the advent of the Internet and social networks, their magnitude has increased and the damage caused to individuals and corporate entities is becoming increasingly greater, even irreparable. In this paper, we tackle the detection of text-based cyberpropaganda using Machine Learning and NLP techniques. We use the eXtreme Gradient Boosting (XGBoost) algorithm for learning and detection, in tandem with Bag-of-Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) for text vectorization. We highlight the contribution of gradient boosting and regularization mechanisms in the performance of the explored model.

scholarly journals Realistic Aspects of Simulation Models for Fake News Epidemics over Social Networks

2021 ◽  
Vol 13 (3) ◽  
pp. 76
Author(s):  
Quintino Francesco Lotito ◽  
Davide Zanella ◽  
Paolo Casari
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Simulation Models ◽  
Epidemic Models ◽  
Time Varying ◽  
Fake News ◽  
Network Access ◽  
Spreading Process ◽  
Network Topologies ◽  
Access Patterns

The pervasiveness of online social networks has reshaped the way people access information. Online social networks make it common for users to inform themselves online and share news among their peers, but also favor the spreading of both reliable and fake news alike. Because fake news may have a profound impact on the society at large, realistically simulating their spreading process helps evaluate the most effective countermeasures to adopt. It is customary to model the spreading of fake news via the same epidemic models used for common diseases; however, these models often miss concepts and dynamics that are peculiar to fake news spreading. In this paper, we fill this gap by enriching typical epidemic models for fake news spreading with network topologies and dynamics that are typical of realistic social networks. Specifically, we introduce agents with the role of influencers and bots in the model and consider the effects of dynamical network access patterns, time-varying engagement, and different degrees of trust in the sources of circulating information. These factors concur with making the simulations more realistic. Among other results, we show that influencers that share fake news help the spreading process reach nodes that would otherwise remain unaffected. Moreover, we emphasize that bots dramatically speed up the spreading process and that time-varying engagement and network access change the effectiveness of fake news spreading.

Fake News im Wahlkampf

2021 ◽  
Author(s):  
Jessica Flint
Keyword(s):  
Social Networks ◽  
Public Opinion ◽  
Fundamental Rights ◽  
Election Campaigns ◽  
Fake News ◽  
Forming Process ◽  
Private Companies ◽  
The Future

The urgency of regulating fake news on social networks regarding election campaigns is more evident than ever. This poses considerable difficulties for legislative practice. It is important to consider the fundamental rights of the parties involved without the state's influence on the formation of public opinion becoming too great. The current options of reacting to fake news do not suffice to ensure a free opinion-forming process. This publication makes an innovative proposal as to how social networks – especially Facebook – can be regulated in the future in such a way that the discourse is strengthened and the alarming influence of private companies on the formation of opinion is limited.

scholarly journals A Study of Rumor Detection based on Social Network Topic Models Relationship

2020 ◽  
Author(s):  
Diogo Nolasco ◽  
Jonice Oliveira
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Local Community ◽  
Topic Model ◽  
Fake News ◽  
Detection Problem ◽  
Model Method ◽  
Show Evidence ◽  
Rumor Detection ◽  
Scientific Topic

The rumor detection problem on social networks has attracted considerable attention in recent years with the rise of concerns about fake news and disinformation. Most previous works focused on detecting rumors by individual messages, classifying whether a post or blog entry is considered a rumor or not. This paper proposes a method for rumor detection on topic-level that identifies whether a social topic related to a scientific topic is a rumor. We propose the use of a topic model method on social and scientific domains and correlate the topics found to detect the most prone to be rumors. Results applied in the Zika epidemic scenario show evidence that the least correlated topics contain a mix of rumors and local community discussions.

scholarly journals The crisis of content verbality in Internet discourse

2021 ◽  
pp. 224-228
Author(s):  
Марина Михайловна Молчанова ◽  
Патимат Абдулаевна Лекова
Keyword(s):  
Social Networks ◽  
Computer Technology ◽  
Linguistic Competence ◽  
The Internet ◽  
The World ◽  
Younger Generation ◽  
Media Texts ◽  
Active Visualization ◽  
First Time

Исследуется кризис вербальности контента в интернет-дискурсе, его активная визуализация, связанная с новыми открытиями в области компьютерных технологий. Цель работы - дать полиаспектную характеристику этому явлению и обозначить перспективы его влияния на речемыслительную деятельность подрастающего поколения, составляющего большую часть пользователей социальных сетей. Актуальность данной проблематики обусловлена обеспокоенностью филологической общественностью тем, что мир становится все менее лингвистическим. Новизна заключается в том, что впервые интернет-дискурс рассматривается в контексте кризиса вербальности контента. При таких темпах визуализации медиатекстов вполне вероятно обострение кризиса вербальности, последствия которого могут негативно сказаться на мыслетворческой деятельности у подрастающего поколения, которая возможна только при высокой языковой компетенции. The paper examines the crisis of content verbality in the Internet discourse, its active visualization associated with new discoveries in the field of computer technology. The aim of the work is to give a multi-aspect characterization of this phenomenon and outline the prospects of its influence on the speech-thinking activity of the younger generation, which makes up the majority of users of social networks. The relevance of this issue is due to the concern of the philological community that the world is becoming less and less linguistic. The novelty lies in the fact that for the first time Internet discourse is considered in the context of the crisis of content verbality. At such a rate of visualization of media texts, it is likely that the crisis of verbality will aggravate, the consequences of which can negatively affect the thinking activity of the younger generation, which is possible only with high linguistic competence.

scholarly journals Penelitian Terhadap Kriteria dan Tekstual Ijazah Sanad Al-Quran

2019 ◽  
Vol 15 (2) ◽  
pp. 76-92
Author(s):  
Norazman Alias ◽  
Khairul Anuar Mohamad
Keyword(s):  
Current Trend ◽  
Arab Countries ◽  
Contemporary Culture ◽  
Proper Understanding ◽  
Written Text ◽  
Home Based ◽  
Other Information ◽  
Deductive Method ◽  
Textual Content

The method of ijazah (permission) sanad (authority) of al-Quran in Malaysia is still relatively unfamiliar and unknown to most people in Malaysia. Perhaps this practice is exclusive to the Quranic teachers, huffaz (who have memorized) of the Quran, and students of higher education. Furthermore, among the Quranic sanad holders are those who have obtained it through the Qur'anic talaqqi (acquisition) program coordinated by organizational authorities within and outside of the country such as Sultan Ismail Petra International Islamic College of Kelantan, Al Mufid Studies Center of Terengganu, Al-Azhar Maahad Qiraat of Egypt, International Islamic University of Madinah and many more. In fact, the current trend shows that many people and scholars in the field of Quranic studies especially from Arab countries have been invited to conduct home-based Quranic talaqqi programs. This is especially the case for programs organized by Ainhafeez Enterprise and Khozandaroh Studies Center of Selangor. These programs contribute more to the understanding of public towards the substantiality of the Quranic ijazah sanad that has been traditionally practiced since the time of revelation. In light of this phenomenon, there are some important issues such as the understanding of the component and the textual content of Quranic sanad among the sanad holders that need to be addressed and refined by the organizers. This process of ijazah sanad is of importance since the textual content is utterly different from other discipline of Islamic sciences like hadith or ijazah of classical turath (heritage) books. Therefore, this study discusses the concept of ijazah sanad of al-Quran as well as the textual content of Quranic sanad. This qualitative study employs library-based and deductive method in analyzing textual content of Quranic sanad in order to fulfill the fundamental characterization of Quranic sanad sciences. The preliminary findings show the diversities of textual content of Quranic sanad all over the world are unbridged from important items of Quranic sanad written text such as title, awarding body and recipient, official stamp and signature including other information. Accordingly, the understanding of textual content of Quranic sanad is essential for its preservation apart from refinement of sharia’s demand and contemporary culture. Having a proper understanding of the Quranic sanad, the transmission of this tradition from one generation to another can be confined within trustees and not be awarded to the outsiders.

scholarly journals Coronavirus in Spain: Fear of ‘Official’ Fake News Boosts WhatsApp and Alternative Sources

2020 ◽  
Vol 8 (2) ◽  
pp. 462-466 ◽  
Author(s):  
Carlos Elías ◽  
Daniel Catalan-Matamoros
Keyword(s):  
Social Networks ◽  
The State ◽  
Fake News ◽  
Public Media ◽  
History Of ◽  
The Media ◽  
Alternative Sources ◽  
Official Sources

The communication of the Coronavirus crisis in Spain has two unexpected components: the rise of the information on social networks, especially WhatsApp, and the consolidation of TV programs on mystery and esotericism. Both have emerged to “tell the truth” in opposition to official sources and public media. For a country with a long history of treating science and the media as properties of the state, this very radical development has surprised communication scholars.

Sign in / Sign up

Export Citation Format

Share Document