@inproceedings{alvarez-ojeda-etal-2025-precom,
title = "The {PRECOM}-{SM} Corpus: Gambling in {S}panish Social Media",
author = "{\'A}lvarez-Ojeda, Pablo and
Cantero-Romero, Mar{\'i}a Victoria and
Semikozova, Anastasia and
Montejo-Raez, Arturo",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.2/",
pages = "17--28",
abstract = "Gambling addiction is a {\textquotedblleft}silent problem{\textquotedblright} in society, especially among young people in recent years due to the easy access to betting and gambling sites on the Internet through smartphones and personal computers. As online communities in messaging apps, forums and other {\textquotedblleft}teenagers gathering{\textquotedblright} sites keep growing day by day, more textual information is available for its study. This work focuses on collecting text from online Spanish-speaking communities and analysing it in order to find patterns in written language from frequent and infrequent users on the collected platforms so that an emerging gambling addiction problem can be detected. In this paper, a newly built corpus is introduced, as well as an extensive description of how it has been made. Besides, some baseline experiments on the data have been carried on, employing the generated features after the analysis of the text with different machine learning approaches like the bag of words model or deep neural network encodings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alvarez-ojeda-etal-2025-precom">
<titleInfo>
<title>The PRECOM-SM Corpus: Gambling in Spanish Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Álvarez-Ojeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Cantero-Romero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Semikozova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Gambling addiction is a “silent problem” in society, especially among young people in recent years due to the easy access to betting and gambling sites on the Internet through smartphones and personal computers. As online communities in messaging apps, forums and other “teenagers gathering” sites keep growing day by day, more textual information is available for its study. This work focuses on collecting text from online Spanish-speaking communities and analysing it in order to find patterns in written language from frequent and infrequent users on the collected platforms so that an emerging gambling addiction problem can be detected. In this paper, a newly built corpus is introduced, as well as an extensive description of how it has been made. Besides, some baseline experiments on the data have been carried on, employing the generated features after the analysis of the text with different machine learning approaches like the bag of words model or deep neural network encodings.</abstract>
<identifier type="citekey">alvarez-ojeda-etal-2025-precom</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.2/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>17</start>
<end>28</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The PRECOM-SM Corpus: Gambling in Spanish Social Media
%A Álvarez-Ojeda, Pablo
%A Cantero-Romero, María Victoria
%A Semikozova, Anastasia
%A Montejo-Raez, Arturo
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F alvarez-ojeda-etal-2025-precom
%X Gambling addiction is a “silent problem” in society, especially among young people in recent years due to the easy access to betting and gambling sites on the Internet through smartphones and personal computers. As online communities in messaging apps, forums and other “teenagers gathering” sites keep growing day by day, more textual information is available for its study. This work focuses on collecting text from online Spanish-speaking communities and analysing it in order to find patterns in written language from frequent and infrequent users on the collected platforms so that an emerging gambling addiction problem can be detected. In this paper, a newly built corpus is introduced, as well as an extensive description of how it has been made. Besides, some baseline experiments on the data have been carried on, employing the generated features after the analysis of the text with different machine learning approaches like the bag of words model or deep neural network encodings.
%U https://aclanthology.org/2025.coling-main.2/
%P 17-28
Markdown (Informal)
[The PRECOM-SM Corpus: Gambling in Spanish Social Media](https://aclanthology.org/2025.coling-main.2/) (Álvarez-Ojeda et al., COLING 2025)
ACL
- Pablo Álvarez-Ojeda, María Victoria Cantero-Romero, Anastasia Semikozova, and Arturo Montejo-Raez. 2025. The PRECOM-SM Corpus: Gambling in Spanish Social Media. In Proceedings of the 31st International Conference on Computational Linguistics, pages 17–28, Abu Dhabi, UAE. Association for Computational Linguistics.