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

By Kai Shu, Deepak Mahudeswaran, Suhang Wang, Dongwon Lee, Huan Liu. Big Data, 2018

1,232 citations recorded by the source corpus.

Social media has become a popular means for people to consume and share the news. At the same time, however, it has also enabled the wide dissemination of fake news, that is, news with intentionally false information, causing significant negative effects on society. To mitigate this problem, the research of fake news detection has recently received a lot of attention. Despite several existing computational solutions on the detection of fake news, the lack of comprehensive and community-driven fake news data sets has become one of major roadblocks. Not only existing data sets are scarce, they do not contain a myriad of features often required in the study such as news content, social context, and spatiotemporal information. Therefore, in this article, to facilitate fake news-related research, we present a fake news data repository FakeNewsNet, which contains two comprehensive data sets with diverse features in news content, social context, and spatiotemporal information. We present a comprehensive description of the FakeNewsNet, demonstrate an exploratory analysis of two data sets from different perspectives, and discuss the benefits of the FakeNewsNet for potential applications on fake news study on social media.

Subfields: Information Systems, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/eed1a4b3ec3b6de0fd1f0b8b2ec969b540fe41a0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Sociology and Political Science

Citations in the corpus

DialFact: A Benchmark for Fact-Checking in Dialogue (2021, background): “, 2020), news articles (Potthast et al., 2018; Shu et al., 2020), and social media claims (Nakov et al.”
FANG: Leveraging Social Context for Fake News Detection Using Graph Representation (2020, methodology): “We conducted our experiments on a Twitter dataset collected by related work on rumor classification [20, 25] and fake news detection [37].”
NewsEmbed: Modeling News through Pre-trained Document Representations (2021, methodology): “People use traditional approaches such as Naive Bayes and Support Vector Machines [15, 54], and neural network approaches such as LSTM [51] and CNN [18].”
Combating Fake News (2019, methodology): “Shu et al. 2018 evaluated the performance of several different methods on two datasets from PolitiFact and GossipCop and reported a maximum detection accuracy of 69% and 79.6% respectively, even when using both article contents and social context i.e. user responses to the article on Twitter.”
A Survey of Fake News (2020, methodology): “…(Accuracy (Acc.) and F 1 -score) in Fake News Detection Using Traditional ML (RF and XGBoost Classifiers) [Zhou et al. 2019a] PolitiFact data [Shu et al. 2018] BuzzFeed data [Shu et al Within the same experimental setup as that in the work of Zhou et al. [2019a], the performance of (latent…”
Explainable Automated Fact-Checking: A Survey (2020, background): “There are also corpora which consist of real-world or naturally occurring claims, including claims from multiple domains, such as Mul-tiFC (Augenstein et al., 2019), FakeNewsNet (Shu et al., 2018), and a corpus with ﬁne-grained evi-1 dence (Hanselowski et al., 2019).”
Fake news, disinformation and misinformation in social media: a review (2023, background): “…(Bringula et al. 2022; Baptista and Gradim 2022; Tsang 2020; Tandoc Jr et al. 2021; Bastick 2021; Khan et al. 2019; Shu et al. 2017; Nakov 2020; Shu et al. 2020c; Egelhofer and Lecheler 2019), while others associate the term with both disinformation and misinformation (Wu et al. 2022; Dame…”
User Perceptions and Trust of Explainable Machine Learning Fake News Detectors (2022, background): “For example, dEFEND is a leading interpretable fake news detector uses both social media posts and user feedback to identify fake news (Shu, Mahudeswaran, Wang, Lee, & Liu, 2018).”
User Preference-aware Fake News Detection (2021, methodology): “Many baseline methods leverage extra information like image information which is not included in the FakeNewsNet [25].”
Human or Machine? A Survey on Machine-Generated Text Detection (2026, unknown): “This corpus contains 5,200 instances, balanced between human-written and ChatGPT-generated fake news selected from nine publicly available corpora for fake news, including FAKENEWSNET [41], LIAR [42], and a synthetic news corpus using ChatGPT.”