Fake News Detection on Social Media using Geometric Deep Learning

Abstract

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 natural language processing algorithms are still missing. Recent studies have empirically 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 convolutional neural networks 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.

Integrating Human-in-the-loop into Swarm Learning for Decentralized Fake News Detection

“…The first dimension is to combine these features to enhance detection performance. Moti et al represented news as a graph containing these three features and utilized graph convolutional networks (GCN) to classify the graph into fake or true [18]. In addition, it is resilience to adversarial attacks since generating adversarial samples on three features is extremely challenging.…”

“…Centralized detection methods dominated this field by X. Dong and L. Qian are with the Center of Excellence in Research and Education for Big Military Data Intelligence (CREDIT Center), Department of Electrical and Computer Engineering, Prairie View A&M University, Texas A&M University System, Prairie View, TX 77446, USA. Email: xidong@pvamu.edu, liqian@pvamu.edu collecting big data to a cloud storage for building highperformance detection models, where deep learning techniques such as convolutional neural networks (CNN), recurrent neural networks (RNN), and deep graph models outperform other techniques [11], [15], [16], [17], [18], [19]. Unfortunately, one potential risk in the procedure of building these methods is to violate user privacy when collecting big data of news in the centralized manner.…”

Frame invariance and scalability of neural operators for partial differential equations

“…Depending on the application, a graph can have attributes/features attached to the nodes and/or edges, and in some cases each graph can have a global attribute. Such specialized neural networks have found several practical applications such as antibiotic discovery [30], physics simulations [31], fake news identification [32], traffic prediction [33] and recommendation systems [34].…”

FacTeR-Check: Semi-automated fact-checking through Semantic Similarity and Natural Language Inference

“…The effects produced by the complex opinion dynamics that occur in these platforms such as polarisation, echo-chambers, peer presure or social influence [47] hinder the process of analysing the propagation of a false claim. Monti et al [48] propose the use of Geometric Deep Learning to detect false claims in Online Social Networks, an approach which allows to take into consideration the propagation as a graph. A similar approach is followed by FakeDetector [49], in this case using a graph neural network and explicit and latent features to represent both text, creators and subjects.…”