@inproceedings{rinaldi-etal-2026-testimole,
title = "{T}esti{M}ole-Conversational: A 30-Billion-Word {I}talian Discussion Board Corpus (1996{--}2024) for Language Modeling and Sociolinguistic Research",
author = "Rinaldi, Matteo and
Varvara, Rossella and
Patti, Viviana",
editor = "Ba{\'n}ski, Piotr and
Knight, Dawn and
Kupietz, Marc and
Witt, Andreas and
Wr{\'o}blewska, Alina",
booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cmlc-1.1/",
doi = "10.63317/5643evropidu",
pages = "1--11",
abstract = "We present TestiMole-Conversational a massive collection of discussion boards messages in the Italian language. The large size of the corpus, almost 30B word-tokens (1996{--}2024), brings challenges in the processing and curation of the resource, but it renders it an ideal dataset for native Italian Large Language Models' pre-training. Furthermore, discussion boards' messages are a relevant resource for linguistic as well as sociological analysis. The corpus captures a rich variety of computer-mediated communication, offering insights into informal written Italian, discourse dynamics, and online social interaction in a wide time span. Beyond its relevance for NLP applications such as language modelling, domain adaptation, and conversational analysis, it also support investigations of language variation and social phenomena in digital communication."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rinaldi-etal-2026-testimole">
<titleInfo>
<title>TestiMole-Conversational: A 30-Billion-Word Italian Discussion Board Corpus (1996–2024) for Language Modeling and Sociolinguistic Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rossella</namePart>
<namePart type="family">Varvara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Patti</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 12th Workshop on Challenges in the Management of Large Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Bański</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kupietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Witt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Wróblewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present TestiMole-Conversational a massive collection of discussion boards messages in the Italian language. The large size of the corpus, almost 30B word-tokens (1996–2024), brings challenges in the processing and curation of the resource, but it renders it an ideal dataset for native Italian Large Language Models’ pre-training. Furthermore, discussion boards’ messages are a relevant resource for linguistic as well as sociological analysis. The corpus captures a rich variety of computer-mediated communication, offering insights into informal written Italian, discourse dynamics, and online social interaction in a wide time span. Beyond its relevance for NLP applications such as language modelling, domain adaptation, and conversational analysis, it also support investigations of language variation and social phenomena in digital communication.</abstract>
<identifier type="citekey">rinaldi-etal-2026-testimole</identifier>
<identifier type="doi">10.63317/5643evropidu</identifier>
<location>
<url>https://aclanthology.org/2026.cmlc-1.1/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TestiMole-Conversational: A 30-Billion-Word Italian Discussion Board Corpus (1996–2024) for Language Modeling and Sociolinguistic Research
%A Rinaldi, Matteo
%A Varvara, Rossella
%A Patti, Viviana
%Y Bański, Piotr
%Y Knight, Dawn
%Y Kupietz, Marc
%Y Witt, Andreas
%Y Wróblewska, Alina
%S Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F rinaldi-etal-2026-testimole
%X We present TestiMole-Conversational a massive collection of discussion boards messages in the Italian language. The large size of the corpus, almost 30B word-tokens (1996–2024), brings challenges in the processing and curation of the resource, but it renders it an ideal dataset for native Italian Large Language Models’ pre-training. Furthermore, discussion boards’ messages are a relevant resource for linguistic as well as sociological analysis. The corpus captures a rich variety of computer-mediated communication, offering insights into informal written Italian, discourse dynamics, and online social interaction in a wide time span. Beyond its relevance for NLP applications such as language modelling, domain adaptation, and conversational analysis, it also support investigations of language variation and social phenomena in digital communication.
%R 10.63317/5643evropidu
%U https://aclanthology.org/2026.cmlc-1.1/
%U https://doi.org/10.63317/5643evropidu
%P 1-11
Markdown (Informal)
[TestiMole-Conversational: A 30-Billion-Word Italian Discussion Board Corpus (1996–2024) for Language Modeling and Sociolinguistic Research](https://aclanthology.org/2026.cmlc-1.1/) (Rinaldi et al., CMLC 2026)
ACL