A Domain-adaptive Pre-training approach for language bias detection in news

Jan David Krieger, Timo Spinde, Terry Ruas, Juhi Kulshrestha, Bela Gipp

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationJCDL 2022 - Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2022
PublisherACM
ISBN (Electronic)9781450393454
DOIs
Publication statusPublished - Jun 2022
MoE publication typeA4 Article in a conference publication
EventACM/IEEE Joint Conference on Digital Libraries - Cologne, Germany
Duration: 20 Jun 202224 Jun 2022
Conference number: 22

Conference

ConferenceACM/IEEE Joint Conference on Digital Libraries
Abbreviated titleJCDL
Country/TerritoryGermany
CityCologne
Period20/06/202224/06/2022

Keywords

  • Domain adaptive
  • Media bias
  • Neural classification
  • News slant
  • Text analysis

Fingerprint

Dive into the research topics of 'A Domain-adaptive Pre-training approach for language bias detection in news'. Together they form a unique fingerprint.

Cite this