A Domain-adaptive Pre-training Approach for Language Bias Detection in News

Media bias is a multi-faceted construct influencing individual behavior and collective decision-making. Slanted news reporting is the result of one-sided and polarized writing which can occur in various forms. In this work, we focus on an important form of media bias, i.e. bias by word choice. Detecting biased word choices is a challenging task due to its linguistic complexity and the lack of representative gold-standard corpora. We present DA-RoBERTa, a new state-of-the-art transformer-based model adapted to the media bias domain which identifies sentence-level bias with an F1 score of 0.814. In addition, we also train, DA-BERT and DA-BART, two more transformer models adapted to the bias domain. Our proposed domain-adapted models outperform prior bias detection approaches on the same data.

Subject (DDC)

004 Computer Science

Keywords

Media bias, news slant, neural classification, text analysis, domain adaptive

Conference

ACM/IEEE Joint Conference on Digital Libraries (JCDL ’22), Jun 20, 2022 - Jun 24, 2022, Köln

Cite This

ISO 690

KRIEGER, Jan-David, Timo SPINDE, Terry RUAS, Juhi KULSHRESTHA, Bela GIPP, 2022. A Domain-adaptive Pre-training Approach for Language Bias Detection in News. ACM/IEEE Joint Conference on Digital Libraries (JCDL ’22). Köln, Jun 20, 2022 - Jun 24, 2022. In: JCDL '22 : Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries. New York, NY:ACM, 3. ISBN 978-1-4503-9345-4. Available under: doi: 10.1145/3529372.3530932

BibTex

@inproceedings{Krieger2022Domai-57523,
  year={2022},
  doi={10.1145/3529372.3530932},
  title={A Domain-adaptive Pre-training Approach for Language Bias Detection in News},
  isbn={978-1-4503-9345-4},
  publisher={ACM},
  address={New York, NY},
  booktitle={JCDL '22 : Proceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries},
  author={Krieger, Jan-David and Spinde, Timo and Ruas, Terry and Kulshrestha, Juhi and Gipp, Bela},
  note={Article Number: 3}
}

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/123456789/57523">
    <dc:contributor>Gipp, Bela</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/57523/1/Krieger_2-1fua1es2xhhxv0.pdf"/>
    <dcterms:issued>2022</dcterms:issued>
    <dc:creator>Ruas, Terry</dc:creator>
    <dc:language>eng</dc:language>
    <dcterms:title>A Domain-adaptive Pre-training Approach for Language Bias Detection in News</dcterms:title>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Krieger, Jan-David</dc:contributor>
    <dc:creator>Spinde, Timo</dc:creator>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/57523"/>
    <dc:creator>Krieger, Jan-David</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-05-12T11:55:32Z</dc:date>
    <dc:creator>Kulshrestha, Juhi</dc:creator>
    <dc:creator>Gipp, Bela</dc:creator>
    <dc:contributor>Spinde, Timo</dc:contributor>
    <dcterms:abstract xml:lang="eng">Media bias is a multi-faceted construct influencing individual behavior and collective decision-making. Slanted news reporting is the result of one-sided and polarized writing which can occur in various forms. In this work, we focus on an important form of media bias, i.e. bias by word choice. Detecting biased word choices is a challenging task due to its linguistic complexity and the lack of representative gold-standard corpora. We present DA-RoBERTa, a new state-of-the-art transformer-based model adapted to the media bias domain which identifies sentence-level bias with an F1 score of 0.814. In addition, we also train, DA-BERT and DA-BART, two more transformer models adapted to the bias domain. Our proposed domain-adapted models outperform prior bias detection approaches on the same data.</dcterms:abstract>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Kulshrestha, Juhi</dc:contributor>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/57523/1/Krieger_2-1fua1es2xhhxv0.pdf"/>
    <dc:contributor>Ruas, Terry</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-05-12T11:55:32Z</dcterms:available>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

Yes