# Hawkes Process for Understanding the Influence of Pathogenic Social Media Accounts

arXiv: https://arxiv.org/abs/1902.01970 · HTML: https://mlsanity.com/paper/1902.01970/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2019.

## Built on by (most cited first, 4 of 4)

- [Cardinality-Regularized Hawkes-Granger Model](https://mlsanity.com/paper/2208.10671/) (2022)
- [Flexible Triggering Kernels for Hawkes Process Modeling](https://mlsanity.com/paper/2202.01869/) (2022)
- [Hawkes-based cryptocurrency forecasting via Limit Order Book data](https://mlsanity.com/paper/2312.16190/) (2023)
- [Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey](https://mlsanity.com/paper/2606.00136/) (2026)

## Abstract (arXiv)

Over the past years, political events and public opinion on the Web have been allegedly manipulated by accounts dedicated to spreading disinformation and performing malicious activities on social media. These accounts hereafter referred to as "Pathogenic Social Media (PSM)" accounts, are often controlled by terrorist supporters, water armies or fake news writers and hence can pose threats to social media and general public. Understanding and analyzing PSMs could help social media firms devise sophisticated and automated techniques that could be deployed to stop them from reaching their audience and consequently reduce their threat. In this paper, we leverage the well-known statistical technique "Hawkes Process" to quantify the influence of PSM accounts on the dissemination of malicious information on social media platforms. Our findings on a real-world ISIS-related dataset from Twitter indicate that PSMs are significantly different from regular users in making a message viral. Specifically, we observed that PSMs do not usually post URLs from mainstream news sources. Instead, their tweets usually receive large impact on audience, if contained URLs from Facebook and alternative news outlets. In contrary, tweets posted by regular users receive nearly equal impression regardless of the posted URLs and their sources. Our findings can further shed light on understanding and detecting PSM accounts.