# Trends in the Diffusion of Misinformation on Social Media

arXiv: https://arxiv.org/abs/1809.05901 · HTML: https://mlsanity.com/paper/1809.05901/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2018.

## Built on by (most cited first, 25 of 25)

- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [Human-AI Coevolution](https://mlsanity.com/paper/2306.13723/) (2023)
- [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](https://mlsanity.com/paper/2212.07425/) (2022)
- [VRoC: Variational Autoencoder-aided Multi-task Rumor Classifier Based on Text](https://mlsanity.com/paper/2102.00816/) (2021)
- [Specious Sites: Tracking the Spread and Sway of Spurious News Stories at Scale](https://mlsanity.com/paper/2308.02068/) (2023)
- [FactFinders at CheckThat! 2024: Refining Check-worthy Statement Detection with LLMs through Data Pruning](https://mlsanity.com/paper/2406.18297/) (2024)
- [Not all Fake News is Written: A Dataset and Analysis of Misleading Video Headlines](https://mlsanity.com/paper/2310.13859/) (2023)
- [LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media](https://mlsanity.com/paper/2504.12325/) (2025)
- [Machine Love](https://mlsanity.com/paper/2302.09248/) (2023)
- [Exoskeleton for the Mind: Exploring Strategies Against Misinformation with a Metacognitive Agent](https://mlsanity.com/paper/2304.08759/) (2023)
- [DGM4+: Dataset Extension for Global Scene Inconsistency](https://mlsanity.com/paper/2509.26047/) (2025)
- [A User-Driven Framework for Regulating and Auditing Social Media](https://mlsanity.com/paper/2304.10525/) (2023)
- [Inside the echo chamber: Linguistic underpinnings of misinformation on Twitter](https://mlsanity.com/paper/2404.15925/) (2024)
- [VERITAS-NLI : Validation and Extraction of Reliable Information Through Automated Scraping and Natural Language Inference](https://mlsanity.com/paper/2410.09455/) (2024)
- [Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility](https://mlsanity.com/paper/2603.03585/) (2026)
- [COVID-19 and Big Data: Multi-faceted Analysis for Spatio-temporal Understanding of the Pandemic with Social Media Conversations](https://mlsanity.com/paper/2104.10807/) (2021)
- [A Hierarchical Network-Oriented Analysis of User Participation in Misinformation Spread on WhatsApp](https://mlsanity.com/paper/2109.10462/) (2021)
- [Bias amplification in experimental social networks is reduced by resampling](https://mlsanity.com/paper/2208.07261/) (2022)
- [Event detection from novel data sources: Leveraging satellite imagery alongside GPS traces](https://mlsanity.com/paper/2401.10890/) (2024)
- [Capturing Pertinent Symbolic Features for Enhanced Content-Based Misinformation Detection](https://mlsanity.com/paper/2401.16285/) (2024)
- [Dhoroni: Exploring Bengali Climate Change and Environmental Views with a Multi-Perspective News Dataset and Natural Language Processing](https://mlsanity.com/paper/2410.17225/) (2024)
- [Evaluating the Propensity of Generative AI for Producing Harmful Disinformation During the 2024 US Election Cycle](https://mlsanity.com/paper/2411.06120/) (2024)
- [Analyzing the temporal dynamics of linguistic features contained in misinformation](https://mlsanity.com/paper/2503.04786/) (2025)
- [It Matters How You Say It: Exploring Rhetorical Patterns for AI-Assisted Information Evaluation](https://mlsanity.com/paper/2607.17627/) (2026)

## Abstract (arXiv)

We measure trends in the diffusion of misinformation on Facebook and Twitter between January 2015 and July 2018. We focus on stories from 570 sites that have been identified as producers of false stories. Interactions with these sites on both Facebook and Twitter rose steadily through the end of 2016. Interactions then fell sharply on Facebook while they continued to rise on Twitter, with the ratio of Facebook engagements to Twitter shares falling by approximately 60 percent. We see no similar pattern for other news, business, or culture sites, where interactions have been relatively stable over time and have followed similar trends on the two platforms both before and after the election.