# TrollHunter [Evader]: Automated Detection [Evasion] of Twitter Trolls During the COVID-19 Pandemic

arXiv: https://arxiv.org/abs/2012.02586 · HTML: https://mlsanity.com/paper/2012.02586/

## Key facts

- Cited by 6 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 4 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Exposing Influence Campaigns in the Age of LLMs: A Behavioral-Based AI Approach to Detecting State-Sponsored Trolls](https://mlsanity.com/paper/2210.08786/) (2022)
- [Studying Fake News Spreading, Polarisation Dynamics, and Manipulation by Bots: a Tale of Networks and Language](https://mlsanity.com/paper/2109.07909/) (2021)
- [Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions](https://mlsanity.com/paper/2110.13980/) (2021)
- ["TL;DR:" Out-of-Context Adversarial Text Summarization and Hashtag Recommendation](https://mlsanity.com/paper/2104.00782/) (2021)
- [A Context-Sensitive Word Embedding Approach for The Detection of Troll Tweets](https://mlsanity.com/paper/2207.08230/) (2022)
- [Unsupervised Anomaly Detection of Information Operations Users via Behavioral and Language Patterns](https://mlsanity.com/paper/2607.05855/) (2026)

## Abstract (arXiv)

This paper presents TrollHunter, an automated reasoning mechanism we used to hunt for trolls on Twitter during the COVID-19 pandemic in 2020. Trolls, poised to disrupt the online discourse and spread disinformation, quickly seized the absence of a credible response to COVID-19 and created a COVID-19 infodemic by promulgating dubious content on Twitter. To counter the COVID-19 infodemic, the TrollHunter leverages a unique linguistic analysis of a multi-dimensional set of Twitter content features to detect whether or not a tweet was meant to troll. TrollHunter achieved 98.5% accuracy, 75.4% precision and 69.8% recall over a dataset of 1.3 million tweets. Without a final resolution of the pandemic in sight, it is unlikely that the trolls will go away, although they might be forced to evade automated hunting. To explore the plausibility of this strategy, we developed and tested an adversarial machine learning mechanism called TrollHunter-Evader. TrollHunter-Evader employs a Test Time Evasion (TTE) approach in a combination with a Markov chain-based mechanism to recycle originally trolling tweets. The recycled tweets were able to achieve a remarkable 40% decrease in the TrollHunter's ability to correctly identify trolling tweets. Because the COVID-19 infodemic could have a harmful impact on the COVID-19 pandemic, we provide an elaborate discussion about the implications of employing adversarial machine learning to evade Twitter troll hunts.