A Machine Learning Approach to Fake News Detection Using Knowledge Verification and Natural Language Processing

Ibrishimova, Marina Danchovsky; Li, Kin Fun

doi:10.1007/978-3-030-29035-1_22

Cited by 47 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second topical area focuses on automated methods for classifying content that contains falsehoods within information environments. For example, one proposed framework for detecting falsehoods analyzes the text (e.g., title length, percentage of proper nouns) and verifies the accuracy of information compared with a corpus of trusted sources (Ibrishimova and Li, 2019). In another study, the authors describe a classifier that estimates the probability that a news story is false using such features as the headline (e.g., whether a news title had capital letters), authorship characteristics, sourcing, origin or publisher, and the content's political perspective (Snell et al, 2019).…”

Section: Three Features Describe How Russia's 'Firehose Of Falsehoods...mentioning

confidence: 99%

From Consensus to Conflict: Understanding Foreign Measures Targeting U.S. Elections

Posard¹,

Kepe²,

Reininger³

et al. 2020

View full text Add to dashboard Cite

T hroughout the remaining U.S. political campaign season of 2020, Russia might try again to manipulate and divide U.S. voters through social media. This report is the first in a four-part series aimed at helping policymakers and the public understand-and mitigate-the threat of online foreign interference in national, state, and local elections. 1 Concerns over foreign influence in U.S. politics date back to the founding of this country. Alexander Hamilton warned about "the desire in foreign powers to gain an improper ascendant in our councils" (Hamilton, 1788). George Washington's farewell speech cautioned that "foreign influence is one of the most baneful foes of republican government" (Washington, 1796). During the Civil War, the Confederacy solicited the support of Britain and France against the Union (Central Intelligence Agency, undated). In 1940, the British covertly intervened in the U.S. presidential election in hopes to garner support for U.S. intervention in World War II (Usdin, 2017). During the Cold War, the Soviet Union operated a sophisticated program involving covert and overt information efforts against the United States (Jones, 2019; Schoen and Lamb, 2012). More recently, the U.S. Senate Committee on Intelligence presented evidence that Russia directed

show abstract

Section: Three Features Describe How Russia's 'Firehose Of Falsehoods...mentioning

confidence: 99%

From Consensus to Conflict: Understanding Foreign Measures Targeting U.S. Elections

Posard¹,

Kepe²,

Reininger³

et al. 2020

View full text Add to dashboard Cite

show abstract

“…They have approached the problem from the perspective of news content and information in social networks, techniques in data mining, machine learning, natural language processing, information retrieval and social search to devise a holistic and automatic tool for the detection of fake news. Ibrishimova and Li (2020) have likewise used a framework for fake news detection based on a machine learning model to define and automate the detection process of fake news. Díaz -García et al (2020) have presented a solution based on Text Mining that identified text patterns related to Twitter tweets that refer to fake news, using a pre -labelled dataset of fake and real tweets during the United States presidential election of 2016.…”

Section: Methodsmentioning

confidence: 99%

Novel technologies and Geopolitical Strategies: Disinformation Narratives in the Countries of the Visegrád Group

Bánkuty-Balogh

2021

Politics in Central Europe

View full text Add to dashboard Cite

In the current media environment of growing information disorder and social media platforms emerging as primary news sources, the creation and spread of disinformation is becoming increasingly easy and cost-effective. The projection of strategic narratives through disinformation campaigns is an important geopolitical tool in the global competition for power and status. We have analysed close to 1,000 individual news pieces from more than 60 different online sources containing disinformation, which originally appeared in one of the V4 languages, using a natural language processing algorithm. We have assessed the frequency of recurring themes within the articles and their relationship structure, to see whether consistent disinformation narratives were to be found among them. Through frequency analysis and relationship charting, we have been able to uncover individual storylines connected to more than ten overarching disinformation narratives. We have also exposed five key meta-narratives present in all Visegrád Countries, which fed into a coherent system of beliefs, such as the envisioned collapse of the European Union or the establishment of a system of Neo-Atlantism, which would permanently divide the continent.

show abstract

“…In this section, we discuss how the algorithm is designed, implemented, and tested. Particularly, we present the cornerstone steps that lead to determining the class of news articles: (1) TFIDF feature selection, which is used to extract bigram features from news articles 23,35 (2) TFIDF bigram-based network model, which we use for training the algorithm before it is able to predict the label of new articles, (3) a supervised machine learning algorithm, which predicts the final label for each news article as a SAFE/DISPUTED COVID-19 news article.…”

Section: Methodsmentioning

confidence: 99%

Fighting the COVID-19 Infodemic with Neonet: A Text-Based Supervised Machine Learning Algorithm

Abdeen¹,

Hamed²,

Wu³

2021

Preprint

View full text Add to dashboard Cite

The spread of the Coronavirus pandemic has been accompanied by an infodemic. The false information that is embedded in the infodemic affects people’s ability to have access to safety and follow proper procedures to mitigate the risks. Here, we present a novel supervised machine learning text mining algorithm that analyzes the content of a given news article and assign a label to it. The NeoNet algorithm is trained by noun-phrases features which contributes a network model. The algorithm was tested on a real-world dataset and predicted the label of never-seem articles and flags ones that are suspicious or disputed. In five different fold comparisons, NeoNet surpassed prominent contemporary algorithm such as Neural Networks, SVM, and Random Forests. The analysis shows that the NeoNet algorithm predicts a label of an article with a 100% precision using a non-pruned model. This highlights the promise of detecting disputed online contents that may contribute negatively to the COVID-19 pandemic. Indeed, using machine learning combined with powerful text mining and network science provide the necessary tools to counter the spread of misinformation, disinformation, fake news, rumors, and conspiracy theories that is associated with the COVID19 Infodemic.

show abstract

A Machine Learning Approach to Fake News Detection Using Knowledge Verification and Natural Language Processing

Cited by 47 publications

References 15 publications

From Consensus to Conflict: Understanding Foreign Measures Targeting U.S. Elections

From Consensus to Conflict: Understanding Foreign Measures Targeting U.S. Elections

Novel technologies and Geopolitical Strategies: Disinformation Narratives in the Countries of the Visegrád Group

Fighting the COVID-19 Infodemic with Neonet: A Text-Based Supervised Machine Learning Algorithm

Contact Info

Product

Resources

About