# Detecting False Rumors from Retweet Dynamics on Social Media

arXiv: https://arxiv.org/abs/2201.13103 · HTML: https://mlsanity.com/paper/2201.13103/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2022.

## Built on by (most cited first, 10 of 10)

- [Memory-Guided Multi-View Multi-Domain Fake News Detection](https://mlsanity.com/paper/2206.12808/) (2022)
- [Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer](https://mlsanity.com/paper/2209.08902/) (2022)
- [Characterizing Multi-Domain False News and Underlying User Effects on Chinese Weibo](https://mlsanity.com/paper/2205.03068/) (2022)
- [HQP: A Human-Annotated Dataset for Detecting Online Propaganda](https://mlsanity.com/paper/2304.14931/) (2023)
- [Fake News Detection Through Graph-based Neural Networks: A Survey](https://mlsanity.com/paper/2307.12639/) (2023)
- [Linguistic-style-aware Neural Networks for Fake News Detection](https://mlsanity.com/paper/2301.02792/) (2023)
- [Semantic Evolvement Enhanced Graph Autoencoder for Rumor Detection](https://mlsanity.com/paper/2404.16076/) (2024)
- [Region-enhanced Deep Graph Convolutional Networks for Rumor Detection](https://mlsanity.com/paper/2206.07665/) (2022)
- [Verifying Rumors via Stance-Aware Structural Modeling](https://mlsanity.com/paper/2512.13559/) (2025)
- [A Survey on Quantitative Modeling of Trust in Online Social Networks](https://mlsanity.com/paper/2603.11054/) (2026)

## Abstract (arXiv)

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, our model obviates the need for feature engineering; instead, it directly models the spreading process in order to make inferences of whether online rumors are incorrect. Our evaluation is based on 13,650 retweet cascades of both true. vs. false rumors from Twitter. Our model recognizes false rumors with a balanced accuracy of 64.97% and an AUC of 69.46%. It outperforms state-of-the-art baselines (both neural and feature engineering) by a considerable margin but while being fully interpretable. Our work has direct implications for practitioners: it leverages the spreading process as an implicit quality signal and, based on it, detects false content.