Publikation:

A machine learning approach to detect potentially harmful and protective suicide-related content in broadcast media

Lade...
Vorschaubild

Dateien

Metzler_2-16x5enbhqjp1k1.pdf
Metzler_2-16x5enbhqjp1k1.pdfGröße: 1.79 MBDownloads: 18

Datum

2024

Autor:innen

Metzler, Hannah
Baginski, Hubert
Niederkrotenthaler, Thomas

Herausgeber:innen

Kontakt

ISSN der Zeitschrift

Electronic ISSN

ISBN

Bibliografische Daten

Verlag

Schriftenreihe

Auflagebezeichnung

ArXiv-ID

Internationale Patentnummer

Link zur Lizenz

Angaben zur Forschungsförderung

Projekt

Open Access-Veröffentlichung
Open Access Gold
Core Facility der Universität Konstanz

Gesperrt bis

Titel in einer weiteren Sprache

Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published

Erschienen in

PLoS ONE. Public Library of Science (PLoS). 2024, 19(5), e0300917. eISSN 1932-6203. Available under: doi: 10.1371/journal.pone.0300917

Zusammenfassung

Suicide-related media content has preventive or harmful effects depending on the specific content. Proactive media screening for suicide prevention is hampered by the scarcity of machine learning approaches to detect specific characteristics in news reports. This study applied machine learning to label large quantities of broadcast (TV and radio) media data according to media recommendations reporting suicide. We manually labeled 2519 English transcripts from 44 broadcast sources in Oregon and Washington, USA, published between April 2019 and March 2020. We conducted a content analysis of media reports regarding content characteristics. We trained a benchmark of machine learning models including a majority classifier, approaches based on word frequency (TF-IDF with a linear SVM) and a deep learning model (BERT). We applied these models to a selection of more simple (e.g., focus on a suicide death), and subsequently to putatively more complex tasks (e.g., determining the main focus of a text from 14 categories). Tf-idf with SVM and BERT were clearly better than the naive majority classifier for all characteristics. In a test dataset not used during model training, F1-scores (i.e., the harmonic mean of precision and recall) ranged from 0.90 for celebrity suicide down to 0.58 for the identification of the main focus of the media item. Model performance depended strongly on the number of training samples available, and much less on assumed difficulty of the classification task. This study demonstrates that machine learning models can achieve very satisfactory results for classifying suicide-related broadcast media content, including multi-class characteristics, as long as enough training samples are available. The developed models enable future large-scale screening and investigations of broadcast media.

Zusammenfassung in einer weiteren Sprache

Fachgebiet (DDC)
320 Politik

Schlagwörter

Konferenz

Rezension
undefined / . - undefined, undefined

Forschungsvorhaben

Organisationseinheiten

Zeitschriftenheft

Zugehörige Datensätze in KOPS

Zitieren

ISO 690METZLER, Hannah, Hubert BAGINSKI, David GARCIA, Thomas NIEDERKROTENTHALER, 2024. A machine learning approach to detect potentially harmful and protective suicide-related content in broadcast media. In: PLoS ONE. Public Library of Science (PLoS). 2024, 19(5), e0300917. eISSN 1932-6203. Verfügbar unter: doi: 10.1371/journal.pone.0300917
BibTex
@article{Metzler2024machi-70102,
  year={2024},
  doi={10.1371/journal.pone.0300917},
  title={A machine learning approach to detect potentially harmful and protective suicide-related content in broadcast media},
  number={5},
  volume={19},
  journal={PLoS ONE},
  author={Metzler, Hannah and Baginski, Hubert and Garcia, David and Niederkrotenthaler, Thomas},
  note={Article Number: e0300917}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/70102">
    <dc:creator>Garcia, David</dc:creator>
    <dc:language>eng</dc:language>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/70102/1/Metzler_2-16x5enbhqjp1k1.pdf"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/70102/1/Metzler_2-16x5enbhqjp1k1.pdf"/>
    <dc:rights>Attribution 4.0 International</dc:rights>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/42"/>
    <dcterms:title>A machine learning approach to detect potentially harmful and protective suicide-related content in broadcast media</dcterms:title>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/42"/>
    <dc:contributor>Metzler, Hannah</dc:contributor>
    <dc:contributor>Niederkrotenthaler, Thomas</dc:contributor>
    <dcterms:abstract>Suicide-related media content has preventive or harmful effects depending on the specific content. Proactive media screening for suicide prevention is hampered by the scarcity of machine learning approaches to detect specific characteristics in news reports. This study applied machine learning to label large quantities of broadcast (TV and radio) media data according to media recommendations reporting suicide. We manually labeled 2519 English transcripts from 44 broadcast sources in Oregon and Washington, USA, published between April 2019 and March 2020. We conducted a content analysis of media reports regarding content characteristics. We trained a benchmark of machine learning models including a majority classifier, approaches based on word frequency (TF-IDF with a linear SVM) and a deep learning model (BERT). We applied these models to a selection of more simple (e.g., focus on a suicide death), and subsequently to putatively more complex tasks (e.g., determining the main focus of a text from 14 categories). Tf-idf with SVM and BERT were clearly better than the naive majority classifier for all characteristics. In a test dataset not used during model training, F1-scores (i.e., the harmonic mean of precision and recall) ranged from 0.90 for celebrity suicide down to 0.58 for the identification of the main focus of the media item. Model performance depended strongly on the number of training samples available, and much less on assumed difficulty of the classification task. This study demonstrates that machine learning models can achieve very satisfactory results for classifying suicide-related broadcast media content, including multi-class characteristics, as long as enough training samples are available. The developed models enable future large-scale screening and investigations of broadcast media.</dcterms:abstract>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-06-12T06:44:49Z</dcterms:available>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/>
    <dc:creator>Baginski, Hubert</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Garcia, David</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-06-12T06:44:49Z</dc:date>
    <dcterms:issued>2024</dcterms:issued>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/70102"/>
    <dc:contributor>Baginski, Hubert</dc:contributor>
    <dc:creator>Niederkrotenthaler, Thomas</dc:creator>
    <dc:creator>Metzler, Hannah</dc:creator>
  </rdf:Description>
</rdf:RDF>

Interner Vermerk

xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter

Kontakt
URL der Originalveröffentl.

Prüfdatum der URL

Prüfungsdatum der Dissertation

Finanzierungsart

Kommentar zur Publikation

Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Ja
Link zu Forschungsdaten
Beschreibung der Forschungsdaten
Data and code to reproduce descriptive analyses and figures, except transcript text data
Diese Publikation teilen