FakeNewsNet: A Data Repository with News Content, Social Context, and Spatiotemporal Information for Studying Fake News on Social Media

Shu, Kai; Mahudeswaran, Deepak; Wang, Suhang; Lee, Dongwon; Liu, Huan

doi:10.1089/big.2020.0062

Cited by 655 publications

(437 citation statements)

References 9 publications

Supporting

Mentioning

417

Contrasting

Unclassified

Order By: Relevance

“…This paper presents a novel fake news detection model which uses both content-based and social features for fake news detection. The proposed model has outperformed existing approaches in the literature and obtained higher accuracies than traditional content-based methods on a publically available standard dataset that was recently published [2].…”

Section: Introductionmentioning

confidence: 85%

“…The proposed model has been tested over the publically available dataset FakeNewsNet that was recently published [2]. We have used both the PolitiFact and BuzzFeed datasets which they provide.…”

Section: A Datasetmentioning

confidence: 99%

“…Our proposed model uses both content-based and social-based features for the effective demarcation of fake news from genuine news articles and has achieved remarkable accuracy on a publically available standard dataset that was recently published [2].…”

Section: Comparisons With Earlier Proposed Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Natural Language Processing based Hybrid Model for Detecting Fake News Using Content-Based Features and Social Features

Bauskar¹,

Badole²,

Jain³

et al. 2019

IJIEEB

View full text Add to dashboard Cite

Internet acts as the best medium for proliferation and diffusion of fake news. Information quality on the internet is a very important issue, but web-scale data hinders the expert's ability to correct much of the inaccurate content or fake content present over these platforms. Thus, a new system of safeguard is needed. Traditional Fake news detection systems are based on content-based features (i.e. analyzing the content of the news) of the news whereas most recent models focus on the social features of news (i.e. how the news is diffused in the network). This paper aims to build a novel machine learning model based on Natural Language Processing (NLP) techniques for the detection of 'fake news' by using both content-based features and social features of news. The proposed model has shown remarkable results and has achieved an average accuracy of 90.62% with F1 Score of 90.33% on a standard dataset.

show abstract

Section: Introductionmentioning

confidence: 85%

Section: A Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Natural Language Processing based Hybrid Model for Detecting Fake News Using Content-Based Features and Social Features

Bauskar¹,

Badole²,

Jain³

et al. 2019

IJIEEB

View full text Add to dashboard Cite

show abstract

“…User responses to a source post (the first message) have been exploited in some rumor detection models. Most studies use four stance categories: [Ma et al, 2016] Twitter15 1,490 y y y y Twitter Tweets from [Liu et al, 2015;Ma et al,2016 [Shu et al, 2019], enhanced from PolitiFact and GossipCop Table 1: Datasets for rumor detection and their properties supporting, denying, querying and commenting. Some studies have explicitly used stance information in their rumor detection model, and have shown big performance improvement (Liu et al, 2015;Enayet and El-Beltagy, 2017;Ma et al, 2018a;Kochkina et al, 2018), including the two systems, (Enayet and El-Beltagy, 2017) and (Li et al, 2019a), that were ranked No.…”

Section: User Stancementioning

confidence: 99%

Rumor Detection on Social Media: Datasets, Methods and Opportunities

Li¹,

Zhang²,

Si³

et al. 2019

Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaga

View full text Add to dashboard Cite

Social media platforms have been used for information and news gathering, and they are very valuable in many applications. However, they also lead to the spreading of rumors and fake news. Many efforts have been taken to detect and debunk rumors on social media by analyzing their content and social context using machine learning techniques. This paper gives an overview of the recent studies in the rumor detection field. It provides a comprehensive list of datasets used for rumor detection, and reviews the important studies based on what types of information they exploit and the approaches they take. And more importantly, we also present several new directions for future research.

show abstract

“…Along with the tweet's content, it consists of topics classified as events or non events that are annotated with ratings stating their credibility [59]. FAKENEWSNET [60] is yet another popular database of News Content and gives a better understanding of how fake news is present on the social media.…”

Section: Related Workmentioning

confidence: 99%

Classification of Fake News by Fine-tuning Deep Bidirectional Transformers based Language Model

Aggarwal¹,

Chauhan²,

Kumar³

et al. 2018

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

With the ever-increasing rate of information dissemination and absorption, "Fake News" has become a real menace. People these days often fall prey to fake news that is in line with their perception. Checking the authenticity of news articles manually is a time-consuming and laborious task, thus, giving rise to the requirement for automated computational tools that can provide insights about degree of fake ness for news articles. In this paper, a Natural Language Processing (NLP) based mechanism is proposed to combat this challenge of classifying news articles as either fake or real. Transfer learning on the Bidirectional Encoder Representations from Transformers (BERT) language model has been applied for this task. This paper demonstrates how even with minimal text pre-processing, the fine-tuned BERT model is robust enough to perform significantly well on the downstream task of classification of news articles. In addition, LSTM and Gradient Boosted Tree models have been built to perform the task and comparative results are provided for all three models. Fine-tuned BERT model could achieve an accuracy of 97.021% on NewsFN data and is able to outperform the other two models by approximately eight percent.

show abstract

FakeNewsNet: A Data Repository with News Content, Social Context, and Spatiotemporal Information for Studying Fake News on Social Media

Cited by 655 publications

References 9 publications

Natural Language Processing based Hybrid Model for Detecting Fake News Using Content-Based Features and Social Features

Natural Language Processing based Hybrid Model for Detecting Fake News Using Content-Based Features and Social Features

Rumor Detection on Social Media: Datasets, Methods and Opportunities

Classification of Fake News by Fine-tuning Deep Bidirectional Transformers based Language Model

Contact Info

Product

Resources

About