Fake News Detection on Social Media using Geometric Deep Learning

By Federico Monti, Fabrizio Frasca, Davide Eynard, Damon Mannion, Michael M. Bronstein. arXiv.org, 2019

566 citations recorded by the source corpus.

Social media are nowadays one of the main news sources for millions of people around the globe due to their low cost, easy access and rapid dissemination. This however comes at the cost of dubious trustworthiness and significant risk of exposure to 'fake news', intentionally written to mislead the readers. Automatically detecting fake news poses challenges that defy existing content-based analysis approaches. One of the main reasons is that often the interpretation of the news requires the knowledge of political or social context or 'common sense', which current NLP algorithms are still missing. Recent studies have shown that fake and real news spread differently on social media, forming propagation patterns that could be harnessed for the automatic fake news detection. Propagation-based approaches have multiple advantages compared to their content-based counterparts, among which is language independence and better resilience to adversarial attacks. In this paper we show a novel automatic fake news detection model based on geometric deep learning. The underlying core algorithms are a generalization of classical CNNs to graphs, allowing the fusion of heterogeneous data such as content, user profile and activity, social graph, and news propagation. Our model was trained and tested on news stories, verified by professional fact-checking organizations, that were spread on Twitter. Our experiments indicate that social network structure and propagation are important features allowing highly accurate (92.7% ROC AUC) fake news detection. Second, we observe that fake news can be reliably detected at an early stage, after just a few hours of propagation. Third, we test the aging of our model on training and testing data separated in time. Our results point to the promise of propagation-based approaches for fake news detection as an alternative or complementary strategy to content-based approaches.

Subfields: Information Systems, Sociology and Political Science, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/318d7da35307221267b6ce6ead995cc812245abb

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

Preserving integrity in online social networks (2020, background): “, deep learning on non-euclidean spaces such as graphs or manifolds) to the problem of detecting misinformation spread on the network [81].”
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects (2020, methodology): “AMSGrad has been used to train CNN in many tasks [101], [102], [103].”
Temporal Graph Networks for Deep Learning on Dynamic Graphs (2020, background): “Graphs are ubiquitously used as models for systems of relations and interactions in many ﬁelds [5, 52, 42, 10, 16, 20, 49, 53], in particular, social sciences [68, 43] and biology [76, 62, 18].”
Utilizing graph machine learning within drug discovery and development (2021, methodology): “These methods have already been successfully applied to a variety of tasks and domains such as recommendation in social media and E-commerce [35–38], traffic estimations in Google Maps [39], misinformation detection in social media [40], and various domains of natural sciences including modelling fl”
A Generalization of Transformer Networks to Graphs (2020, background): “…network architectures on graph datasets and have achieved signiﬁcant success on a wide range of applications, such as in knowledge graphs (Schlichtkrull et al. 2018; Chami et al. 2020), in social sciences (Monti et al. 2019), in physics (Cranmer et al. 2019; Sanchez-Gonzalez et al. 2020), etc.”
A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation (2021, background): “…to identify deliberate disin-formation in a reference-free manner on social media and usually involves common-sense and world knowledge reasoning (Monti et al., 2019), or fact checking (Thorne et al., 2018), where practitioners are asked to verify given claims without references by retrieving…”
User Preference-aware Fake News Detection (2021, methodology): “For example, SAFE [36] and FakeBERT [11] used the TextCNN [35] and BERT [5, 28, 29] to encode the news textual information, respectively; GCNFN [17] and GNN-CL [8] leveraged the GCN [14] to encode the news propagation patterns on social media (e.g., news sharing cascading among social media accounts”
An exploratory study of COVID-19 misinformation on Twitter (2020, unknown): “In our study, we employ an alternative, complementary approach also used by [25,28,29]; We rely on the verdicts of professional fact-checking organisations which manually check each claim.”
Graph Neural Networks with Learnable Structural and Positional Representations (2021, background): “…have shown great promises to be impactful in diverse domains such as drug design (Stokes et al., 2020; Gaudelet et al., 2020), social networks (Monti et al., 2019; Pal et al., 2020), traffic networks (Derrow-Pinion et al., 2021), physics (Cranmer et al., 2019; Bapst et al., 2020),…”
FANG: Leveraging Social Context for Fake News Detection Using Graph Representation (2020, methodology): “Other graphical approaches using matrix factorization [39] or graph convolutional layers [10, 29] learn parameters whose dimensionality is fixed to the network size N , and can be as expensive asO (N 3) [10] in terms of inference time complexity.”
Geometric deep learning on molecular representations (2021, methodology): “First, deep learning methods can cope with "unstructured" data representations, such as text sequences [8, 9], speech signals [10, 11], images [12–14], and graphs [15, 16].”
Prebunking interventions based on the psychological theory of “inoculation” can reduce susceptibility to misinformation across cultures. (2020, background): “Common approaches to tackling the problem of online misinformation include developing and improving detection algorithms (Monti et al., 2019), introducing or amending legislation (Human Rights Watch, 2018), developing and improving fact-checking mechanisms (Nyhan & Reifler, 2012), and focusing on…”