# Mapping the Italian Telegram Ecosystem: Communities, Toxicity, and Hate Speech

arXiv: https://arxiv.org/abs/2504.19594 · HTML: https://mlsanity.com/paper/2504.19594/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 76 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [HelpSteer2-Preference: Complementing Ratings with Preferences](https://mlsanity.com/paper/2410.01257/) (2024)
- [Analyzing the Targets of Hate in Online Social Media](https://mlsanity.com/paper/1603.07709/) (2016)
- [Nemotron-4 15B Technical Report](https://mlsanity.com/paper/2402.16819/) (2024)
- [Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media](https://mlsanity.com/paper/2304.03087/) (2023)
- [The Structure of Toxic Conversations on Twitter](https://mlsanity.com/paper/2105.11596/) (2021)
- [Generalized Word Shift Graphs: A Method for Visualizing and Explaining Pairwise Comparisons Between Texts](https://mlsanity.com/paper/2008.02250/) (2020)
- [Toxic Bias: Perspective API Misreads German as More Toxic](https://mlsanity.com/paper/2312.12651/) (2023)
- [Stance Detection: A Practical Guide to Classifying Political Beliefs in Text](https://mlsanity.com/paper/2305.01723/) (2023)
- [Charting the Landscape of Online Cryptocurrency Manipulation](https://mlsanity.com/paper/2001.10289/) (2020)
- [On the Globalization of the QAnon Conspiracy Theory Through Telegram](https://mlsanity.com/paper/2105.13020/) (2021)
- [The Pushshift Telegram Dataset](https://mlsanity.com/paper/2001.08438/) (2020)
- [Introducing an Abusive Language Classification Framework for Telegram to Investigate the German Hater Community](https://mlsanity.com/paper/2109.07346/) (2021)
- [Temporal Dynamics of Coordinated Online Behavior: Stability, Archetypes, and Influence](https://mlsanity.com/paper/2301.06774/) (2023)
- [An Exploratory Analysis of COVID Bot vs Human Disinformation Dissemination stemming from the Disinformation Dozen on Telegram](https://mlsanity.com/paper/2402.14203/) (2024)
- [Towards Measuring Adversarial Twitter Interactions against Candidates in the US Midterm Elections](https://mlsanity.com/paper/2005.04411/) (2020)
- [Unraveling the Italian and English Telegram Conspiracy Spheres through Message Forwarding](https://mlsanity.com/paper/2404.18602/) (2024)
- [Unearthing a Billion Telegram Posts about the 2024 U.S. Presidential Election: Development of a Public Dataset](https://mlsanity.com/paper/2410.23638/) (2024)

## Built on by (most cited first, 2 of 2)

- [Quantifying Feature Importance for Online Content Moderation](https://mlsanity.com/paper/2510.19882/) (2025)
- [ThreatCore: A Benchmark for Explicit and Implicit Threat Detection](https://mlsanity.com/paper/2605.10563/) (2026)

## Abstract (arXiv)

Telegram has become a major space for political discourse and alternative media. However, its lack of moderation allows misinformation, extremism, and toxicity to spread. While prior research focused on these particular phenomena or topics, these have mostly been examined separately, and a broader understanding of the Telegram ecosystem is still missing. In this work, we fill this gap by conducting a large-scale analysis of the Italian Telegram sphere, leveraging a dataset of 186 million messages from 13,151 chats collected in 2023. Using network analysis, Large Language Models, and toxicity detection tools, we examine how different thematic communities form, align ideologically, and engage in harmful discourse within the Italian cultural context. Results show strong thematic and ideological homophily. We also identify mixed ideological communities where far-left and far-right rhetoric coexist on particular geopolitical issues. Beyond political analysis, we find that toxicity, rather than being isolated in a few extreme chats, appears widely normalized within highly toxic communities. Moreover, we find that Italian discourse primarily targets Black people, Jews, and gay individuals independently of the topic. Finally, we uncover common trend of intra-national hostility, where Italians often attack other Italians, reflecting regional and intra-regional cultural conflicts that can be traced back to old historical divisions. This study provides the first large-scale mapping of the Italian Telegram ecosystem, offering insights into ideological interactions, toxicity, and identity-targets of hate and contributing to research on online toxicity across different cultural and linguistic contexts on Telegram.