PropertyValue
?:abstract
  • Biased population samples pose a prevalent problem in the social sciences. Therefore, we present two novel methods that are based on positive-unlabeled learning to mitigate bias. Both methods leverage auxiliary information from a representative data set and train machine learning classifiers to determine the sample weights. The first method, named maximum representative subsampling (MRS), uses a classifier to iteratively remove instances, by assigning a sample weight of 0, from the biased data set until it aligns with the representative one. The second method is a variant of MRS – Soft-MRS – that iteratively adapts sample weights instead of removing samples completely. To assess the effectiveness of our approach, we induced artificial bias in a public census data set and examined the corrected estimates. We compare the performance of our methods against existing techniques, evaluating the ability of sample weights created with Soft-MRS or MRS to minimize differences and improve downstream classification tasks. Lastly, we demonstrate the applicability of the proposed methods in a real-world study of resilience research, exploring the influence of resilience on voting behavior. Through our work, we address the issue of bias in social science, amongst others, and provide a versatile methodology for bias reduction based on machine learning. Based on our experiments, we recommend to use MRS for downstream classification tasks and Soft-MRS for downstream tasks where the relative bias of the dependent variable is relevant. (xsd:string)
?:author
?:comment
  • (Mikrozensus) (xsd:string)
?:dataSource
  • Mikrozensus-Bibliography (xsd:string)
?:dateModified
  • 2023 (xsd:gyear)
?:datePublished
  • 2023 (xsd:gyear)
?:doi
  • 10.1038/s41598-023-48177-3 ()
?:duplicate
?:fromPage
  • 1 (xsd:string)
is ?:hasPart of
?:inLanguage
  • english (xsd:string)
?:isPartOf
?:issn
  • 20452322 ()
?:issueNumber
  • 1 (xsd:string)
is ?:mainEntity of
?:name
  • Discriminative machine learning for maximal representative subsampling (xsd:string)
?:publicationType
  • article (xsd:string)
?:reference
?:sourceInfo
  • Bibsonomy (xsd:string)
  • In Scientific Reports, 13(1), 1-13, 2023 (xsd:string)
?:studyGroup
  • Mikrozensus (MZ) (xsd:string)
?:tags
  • 2023 (xsd:string)
  • CCBY (xsd:string)
  • FDZ_GML (xsd:string)
  • MZ_input2023 (xsd:string)
  • MZ_pro (xsd:string)
  • Mikrozensus (xsd:string)
  • OA_SSOAR (xsd:string)
  • OAproved (xsd:string)
  • SCIEindexed (xsd:string)
  • SCOPUSindexed (xsd:string)
  • article (xsd:string)
  • english (xsd:string)
  • indexproved (xsd:string)
  • review_proved (xsd:string)
  • reviewed (xsd:string)
  • rp (xsd:string)
  • transfer23 (xsd:string)
?:toPage
  • 13 (xsd:string)
rdf:type
?:url
?:volumeNumber
  • 13 (xsd:string)