Detecting False Rumors from Retweet Dynamics on Social Media

  title={Detecting False Rumors from Retweet Dynamics on Social Media},
  author={Christof Naumzik and Stefan Feuerriegel},
  journal={Proceedings of the ACM Web Conference 2022},
False rumors are known to have detrimental effects on society. To prevent the spread of false rumors, social media platforms such as Twitter must detect them early. In this work, we develop a novel probabilistic mixture model that classifies true vs. false rumors based on the underlying spreading process. Specifically, our model is the first to formalize the self-exciting nature of true vs. false retweeting processes. This results in a novel mixture marked Hawkes model (MMHM). Owing to this… 

Figures and Tables from this paper

Mechanisms of True and False Rumor Sharing in Social Media: Wisdom-of-Crowds or Herd Behavior?

Social media platforms disseminate extensive volumes of online content, including true and, in particular, false rumors. Previous literature has studied the diffusion of offline rumors, yet more

The Virality of Hate Speech on Social Media

Important determinants that explain differences in the spreading of hateful vs. normal content are identified and novel insights into the virality of hate speech on social media are offered.

Region-enhanced Deep Graph Convolutional Networks for Rumor Detection

A novel region-enhanced deep graph convolutional network (RDGCN) that enhances the propagation features of rumors by learning regionalized propagation patterns and trains to learn the propagation patterns by unsupervised learning is proposed.

Online Emotions During the Storming of the U.S. Capitol: Evidence from the Social Media Network Parler

The emotion dynamics on Parler during the storming with regard to heterogeneity across time and users is examined to provide a comprehensive assessment of online emotions and offer important implications for actively managing online emotions to prevent similar in- cidents in the future.

Finding Qs: Profiling QAnon Supporters on Parler

The social media platform “Parler” has emerged into a prominent fringe community where a significant part of the user base are self-reported supporters of QAnon, a far-right conspiracy theory

Memory-Guided Multi-View Multi-Domain Fake News Detection

A Memory-guided Multi-view Multi-domain Fake News Detection Framework to simultaneously detect fake news of multiple domains and poses two challenges in multi-domain fake news detection.

Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer

A Domain- and Instance-level Transfer Framework for Fake News Detection (DITFEND) is proposed, which could improve the performance of specific target domains and shows superior effectiveness for fake news detection.

Linguistic-style-aware Neural Networks for Fake News Detection

—We propose the hierarchical recursive neural net- work (HERO) to predict fake news by learning its linguistic style, which is distinguishable from the truth, as psychological theories reveal. We

AdaDebunk: An Efficient and Reliable Deep State Space Model for Adaptive Fake News Early Detection

This work proposes a novel efficient and reliable deep state space model, namely AdaDebunk, which models the complex probabilistic dependencies and a Bayes' theorem-based dynamic inference algorithm is designed to infer the ADPs and veracity, supporting the accumulation of multi-aspect clues.



Rumor Gauge

The ability to track rumors and predict their outcomes may have practical applications for news consumers, financial markets, journalists, and emergency services, and more generally to help minimize the impact of false information on Twitter.

Automatic detection and verification of rumors on Twitter

The ability to track rumors and predict their outcomes may have practical applications for news consumers, financial markets, journalists, and emergency services, and more generally to help minimize the impact of false information on Twitter.

The spread of true and false news online

A large-scale analysis of tweets reveals that false rumors spread further and faster than the truth, and false news was more novel than true news, which suggests that people were more likely to share novel information.

Rumor Cascades

It is found that rumor cascades run deeper in the social network than reshare cascades in general and that different variants tend to dominate different bursts in popularity.

Detecting Rumors from Microblogs with Recurrent Neural Networks

A novel method that learns continuous representations of microblog events for identifying rumors based on recurrent neural networks that detects rumors more quickly and accurately than existing techniques, including the leading online rumor debunking services.

Detection and Resolution of Rumours in Social Media

This article introduces and discusses two types of rumours that circulate on social media: long-standing rumours that circulating for long periods of time, and newly emerging rumours spawned during fast-paced events such as breaking news, where reports are released piecemeal and often with an unverified status in their early stages.

Prominent Features of Rumor Propagation in Online Social Media

A new periodic time series model that considers daily and external shock cycles, where the model demonstrates that rumor likely have fluctuations over time, and key structural and linguistic differences in the spread of rumors and non-rumors are identified.

Information credibility on twitter

There are measurable differences in the way messages propagate, that can be used to classify them automatically as credible or not credible, with precision and recall in the range of 70% to 80%.

Hoaxy: A Platform for Tracking Online Misinformation

Haxy is introduced, a platform for the collection, detection, and analysis of online misinformation and its related fact-checking efforts, and a preliminary analysis of a sample of public tweets containing both fake news and fact checking is presented.

Rumor Detection over Varying Time Windows

This study determines the major difference between rumors and non-rumors and explores rumor classification performance levels over varying time windows—from the first three days to nearly two months.