@inproceedings{laken-etal-2026-mute,
title = "Mute Cods: A Multilingual Telegram Dataset with Benchmark Models for Conspiracy Theory Detection",
author = "Laken, Katarina and
Marino, Erik Bran and
Piot, Paloma and
Bassi, Davide and
Fomsgaard, S{\o}ren Kirkegaard and
Maggini, Michele Joshua and
Vieira, Renata and
Garcia, Marcos and
Tonelli, Sara",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.582/",
doi = "10.63317/48xmoewrde3v",
pages = "7345--7358",
abstract = "The proliferation of conspiracy theories and hateful messages on social media poses significant challenges for content moderation and public discourse. Despite their societal impact, existing datasets for automated conspiracy detection remain limited in scope and language coverage. We present a multilingual dataset of conspiracy content on Telegram comprising 5750 messages across English, Dutch, Italian, Spanish and Portuguese from 87 channels documented as disseminating conspiracist and extremist content. Domain experts annotated messages for conspiracist tone, population replacement conspiracy theories, vaccine conspiracies, and hate speech. We extensively report on difficulties and caveats when creating and annotating this type of dataset. We establish classification baselines by evaluating six models in zero-shot fashion and fine-tuning three encoder models, achieving F1 scores up to 0.800 for conspiracist tone, 0.846 for PRCT, 0.843 for vaccine-related conspiracy theories, and 0.734 for hate speech. Inter-annotator agreement was moderate, consistent with the complexity documented in similar annotation tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laken-etal-2026-mute">
<titleInfo>
<title>Mute Cods: A Multilingual Telegram Dataset with Benchmark Models for Conspiracy Theory Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katarina</namePart>
<namePart type="family">Laken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="given">Bran</namePart>
<namePart type="family">Marino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paloma</namePart>
<namePart type="family">Piot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Bassi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Søren</namePart>
<namePart type="given">Kirkegaard</namePart>
<namePart type="family">Fomsgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="given">Joshua</namePart>
<namePart type="family">Maggini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renata</namePart>
<namePart type="family">Vieira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Tonelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The proliferation of conspiracy theories and hateful messages on social media poses significant challenges for content moderation and public discourse. Despite their societal impact, existing datasets for automated conspiracy detection remain limited in scope and language coverage. We present a multilingual dataset of conspiracy content on Telegram comprising 5750 messages across English, Dutch, Italian, Spanish and Portuguese from 87 channels documented as disseminating conspiracist and extremist content. Domain experts annotated messages for conspiracist tone, population replacement conspiracy theories, vaccine conspiracies, and hate speech. We extensively report on difficulties and caveats when creating and annotating this type of dataset. We establish classification baselines by evaluating six models in zero-shot fashion and fine-tuning three encoder models, achieving F1 scores up to 0.800 for conspiracist tone, 0.846 for PRCT, 0.843 for vaccine-related conspiracy theories, and 0.734 for hate speech. Inter-annotator agreement was moderate, consistent with the complexity documented in similar annotation tasks.</abstract>
<identifier type="citekey">laken-etal-2026-mute</identifier>
<identifier type="doi">10.63317/48xmoewrde3v</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.582/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7345</start>
<end>7358</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mute Cods: A Multilingual Telegram Dataset with Benchmark Models for Conspiracy Theory Detection
%A Laken, Katarina
%A Marino, Erik Bran
%A Piot, Paloma
%A Bassi, Davide
%A Fomsgaard, Søren Kirkegaard
%A Maggini, Michele Joshua
%A Vieira, Renata
%A Garcia, Marcos
%A Tonelli, Sara
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F laken-etal-2026-mute
%X The proliferation of conspiracy theories and hateful messages on social media poses significant challenges for content moderation and public discourse. Despite their societal impact, existing datasets for automated conspiracy detection remain limited in scope and language coverage. We present a multilingual dataset of conspiracy content on Telegram comprising 5750 messages across English, Dutch, Italian, Spanish and Portuguese from 87 channels documented as disseminating conspiracist and extremist content. Domain experts annotated messages for conspiracist tone, population replacement conspiracy theories, vaccine conspiracies, and hate speech. We extensively report on difficulties and caveats when creating and annotating this type of dataset. We establish classification baselines by evaluating six models in zero-shot fashion and fine-tuning three encoder models, achieving F1 scores up to 0.800 for conspiracist tone, 0.846 for PRCT, 0.843 for vaccine-related conspiracy theories, and 0.734 for hate speech. Inter-annotator agreement was moderate, consistent with the complexity documented in similar annotation tasks.
%R 10.63317/48xmoewrde3v
%U https://aclanthology.org/2026.lrec-1.582/
%U https://doi.org/10.63317/48xmoewrde3v
%P 7345-7358
Markdown (Informal)
[Mute Cods: A Multilingual Telegram Dataset with Benchmark Models for Conspiracy Theory Detection](https://aclanthology.org/2026.lrec-1.582/) (Laken et al., LREC 2026)
ACL
- Katarina Laken, Erik Bran Marino, Paloma Piot, Davide Bassi, Søren Kirkegaard Fomsgaard, Michele Joshua Maggini, Renata Vieira, Marcos Garcia, and Sara Tonelli. 2026. Mute Cods: A Multilingual Telegram Dataset with Benchmark Models for Conspiracy Theory Detection. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 7345–7358, Palma de Mallorca, Spain. ELRA Language Resource Association.