Some Like it Hoax: Automated Fake News Detection in Social Networks
By Eugenio Tacchini, Gabriele Ballarin, Marco L. Della Vedova, Stefano Moret, Luca de Alfaro. arXiv.org, 2017
429 citations recorded by the source corpus.
In recent years, the reliability of information on the Internet has emerged as a crucial issue of modern society. Social network sites (SNSs) have revolutionized the way in which information is spread by allowing users to freely share content. As a consequence, SNSs are also increasingly used as vectors for the diffusion of misinformation and hoaxes. The amount of disseminated information and the rapidity of its diffusion make it practically impossible to assess reliability in a timely manner, highlighting the need for automatic hoax detection systems. As a contribution towards this objective, we show that Facebook posts can be classified with high accuracy as hoaxes or non-hoaxes on the basis of the users who "liked" them. We present two classification techniques, one based on logistic regression, the other on a novel adaptation of boolean crowdsourcing algorithms. On a dataset consisting of 15,500 Facebook posts and 909,236 users, we obtain classification accuracies exceeding 99% even when the training set contains less than 1% of the posts. We further show that our techniques are robust: they work even when we restrict our attention to the users who like both hoax and non-hoax posts. These results suggest that mapping the diffusion pattern of information can be a useful component of automatic hoax detection systems.
Subfields: Information Systems, Sociology and Political Science, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/35d395a89d5859a23e40666e0e90cdd5e0e48da9
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
In Statistical and Nonlinear Physics
Citations in the corpus
- FakeNewsNet: A Data Repository with News Content, Social Context, and Spatiotemporal Information for Studying Fake News on Social Media (2018, neutral): “FacebookHoax 12 : This dataset (Tacchini et al. 2017) comprises information related to posts from the facebook pages related to scientific news (non-hoax) and conspir-acy pages (hoax) collected using Facebook Graph API.”
- dEFEND: Explainable Fake News Detection (2019, background): “Post-based features represent users’ social response in term of stances [43], topics [13], or credibility [18].”
- Fake News: A Survey of Research, Detection Methods, and Opportunities (2018, background): “2018], user features [Jin et al. 2017a; Tacchini et al. 2017], cascade/network features [Kwon et al.”
- Fake News Detection on Social Media: A Data Mining Perspective (2017, background): “The stance network can be built with nodes indicating all the tweets relevant to the news and the edge indicating the weights of similarity of stances [37; 75].”
- A survey on fake news and rumour detection techniques (2019, methodology): “In [88], algorithms derived from crowdsourcing have been used for classification of Facebook posts as hoaxes or non hoaxes.”
- A Survey on Natural Language Processing for Fake News Detection (2018, background): “…of this dataset are that the articles are collected from both sides of left-leaning and right-leaning organizations, and they are enriched in (Tacchini et al., 2017) consists of 15,500 posts from 32 Facebook pages, that is, the public profile of organizations (14 conspiracy and 18 scientific…”
- EANN: Event Adversarial Neural Networks for Multi-Modal Fake News Detection (2018, background): “Thus far, various fake news detection approaches, including both traditional learning [6, 15, 29] and deep learning based models [21, 25], have been exploited to identify fake news.”
- Geometric deep learning (2016, methodology): “One head of graph attention (Velickovic et al. (2018)) was used in every convolutional layer to implement the filters together with mean-pooling for dimensionality reduction.”
- Combating Fake News (2019, methodology): “[109] construct a feature vector consisting of the set of users who liked (responded) the source article or post and used these feature vectors to train a logistic regression model for classification of the source article or post as fake.”