<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zevallos-etal-2025-first">
    <titleInfo>
        <title>The First Multilingual Model For The Detection of Suicide Texts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rodolfo</namePart>
        <namePart type="given">Joel</namePart>
        <namePart type="family">Zevallos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Annika</namePart>
        <namePart type="given">Marie</namePart>
        <namePart type="family">Schoene</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="given">E</namePart>
        <namePart type="family">Ortega</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 Second Workshop on Scaling Up Multilingual &amp; Multi-Cultural Evaluation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Suicidal ideation is a serious health problem affecting millions of people worldwide. Social networks provide information about these mental health problems through users’ emotional expressions. We propose a multilingual model leveraging transformer architectures like mBERT, XML-R, and mT5 to detect suicidal text across posts in six languages - Spanish, English, German, Catalan, Portuguese and Italian. A Spanish suicide ideation tweet dataset was translated into five other languages using SeamlessM4T. Each model was fine-tuned on this multilingual data and evaluated across classification metrics. Results showed mT5 achieving the best performance overall with F1 scores above 85%, highlighting capabilities for cross-lingual transfer learning. The English and Spanish translations also displayed high quality based on perplexity. Our exploration underscores the importance of considering linguistic diversity in developing automated multilingual tools to identify suicidal risk. Limitations exist around semantic fidelity in translations and ethical implications which provide guidance for future human-in-the-loop evaluations.</abstract>
    <identifier type="citekey">zevallos-etal-2025-first</identifier>
    <location>
        <url>https://aclanthology.org/2025.sumeval-2.1/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>1</start>
            <end>11</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The First Multilingual Model For The Detection of Suicide Texts
%A Zevallos, Rodolfo Joel
%A Schoene, Annika Marie
%A Ortega, John E.
%S Proceedings of the Second Workshop on Scaling Up Multilingual & Multi-Cultural Evaluation
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi
%F zevallos-etal-2025-first
%X Suicidal ideation is a serious health problem affecting millions of people worldwide. Social networks provide information about these mental health problems through users’ emotional expressions. We propose a multilingual model leveraging transformer architectures like mBERT, XML-R, and mT5 to detect suicidal text across posts in six languages - Spanish, English, German, Catalan, Portuguese and Italian. A Spanish suicide ideation tweet dataset was translated into five other languages using SeamlessM4T. Each model was fine-tuned on this multilingual data and evaluated across classification metrics. Results showed mT5 achieving the best performance overall with F1 scores above 85%, highlighting capabilities for cross-lingual transfer learning. The English and Spanish translations also displayed high quality based on perplexity. Our exploration underscores the importance of considering linguistic diversity in developing automated multilingual tools to identify suicidal risk. Limitations exist around semantic fidelity in translations and ethical implications which provide guidance for future human-in-the-loop evaluations.
%U https://aclanthology.org/2025.sumeval-2.1/
%P 1-11

Markdown (Informal)

[The First Multilingual Model For The Detection of Suicide Texts](https://aclanthology.org/2025.sumeval-2.1/) (Zevallos et al., SUMEval 2025)

• The First Multilingual Model For The Detection of Suicide Texts (Zevallos et al., SUMEval 2025)

ACL

• Rodolfo Joel Zevallos, Annika Marie Schoene, and John E. Ortega. 2025. The First Multilingual Model For The Detection of Suicide Texts. In Proceedings of the Second Workshop on Scaling Up Multilingual & Multi-Cultural Evaluation, pages 1–11, Abu Dhabi. Association for Computational Linguistics.