Matches in SemOpenAlex for { <https://semopenalex.org/work/W2979746687> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2979746687 endingPage "1" @default.
- W2979746687 startingPage "1" @default.
- W2979746687 abstract "Persons with disabilities face many barriers to full participation in society, and the rapid advancement of technology has the potential to create ever more. Building equitable and inclusive technologies for people with disabilities demands paying attention to more than accessibility, but also to how social attitudes towards disability are represented within technology. Representations perpetuated by machine learning (ML) models often inadvertently encode undesirable social biases from the data on which they are trained. This can result, for example, in text classification models producing very different predictions for I am a person with mental illness , and I am a tall person . In this paper, we present evidence of such biases in existing ML models, and in data used for model development. First, we demonstrate that a machine-learned model to moderate conversations classifies texts which mention disability as more toxic. Similarly, a machine-learned sentiment analysis model rates texts which mention disability as more negative. Second, we demonstrate that neural text representation models that are critical to many ML applications can also contain undesirable biases towards mentions of disabilities. Third, we show that the data used to develop such models reflects topical biases in social discourse which may explain such biases in the models - for instance, gun violence, homelessness, and drug addiction are over-represented in discussions about mental illness." @default.
- W2979746687 created "2019-10-18" @default.
- W2979746687 creator A5019297976 @default.
- W2979746687 creator A5045383831 @default.
- W2979746687 creator A5049223617 @default.
- W2979746687 creator A5071599724 @default.
- W2979746687 creator A5088789058 @default.
- W2979746687 creator A5088842522 @default.
- W2979746687 date "2020-03-02" @default.
- W2979746687 modified "2023-10-02" @default.
- W2979746687 title "Unintended machine learning biases as social barriers for persons with disabilitiess" @default.
- W2979746687 cites W2482604113 @default.
- W2979746687 cites W2898970033 @default.
- W2979746687 doi "https://doi.org/10.1145/3386296.3386305" @default.
- W2979746687 hasPublicationYear "2020" @default.
- W2979746687 type Work @default.
- W2979746687 sameAs 2979746687 @default.
- W2979746687 citedByCount "10" @default.
- W2979746687 countsByYear W29797466872020 @default.
- W2979746687 countsByYear W29797466872021 @default.
- W2979746687 countsByYear W29797466872022 @default.
- W2979746687 countsByYear W29797466872023 @default.
- W2979746687 crossrefType "journal-article" @default.
- W2979746687 hasAuthorship W2979746687A5019297976 @default.
- W2979746687 hasAuthorship W2979746687A5045383831 @default.
- W2979746687 hasAuthorship W2979746687A5049223617 @default.
- W2979746687 hasAuthorship W2979746687A5071599724 @default.
- W2979746687 hasAuthorship W2979746687A5088789058 @default.
- W2979746687 hasAuthorship W2979746687A5088842522 @default.
- W2979746687 hasConcept C119857082 @default.
- W2979746687 hasConcept C134362201 @default.
- W2979746687 hasConcept C136764020 @default.
- W2979746687 hasConcept C144024400 @default.
- W2979746687 hasConcept C154945302 @default.
- W2979746687 hasConcept C15744967 @default.
- W2979746687 hasConcept C169760540 @default.
- W2979746687 hasConcept C17744445 @default.
- W2979746687 hasConcept C180747234 @default.
- W2979746687 hasConcept C199539241 @default.
- W2979746687 hasConcept C2522767166 @default.
- W2979746687 hasConcept C2776359362 @default.
- W2979746687 hasConcept C2776674806 @default.
- W2979746687 hasConcept C2776889888 @default.
- W2979746687 hasConcept C2779304628 @default.
- W2979746687 hasConcept C36289849 @default.
- W2979746687 hasConcept C41008148 @default.
- W2979746687 hasConcept C48856860 @default.
- W2979746687 hasConcept C518677369 @default.
- W2979746687 hasConcept C542102704 @default.
- W2979746687 hasConcept C94625758 @default.
- W2979746687 hasConceptScore W2979746687C119857082 @default.
- W2979746687 hasConceptScore W2979746687C134362201 @default.
- W2979746687 hasConceptScore W2979746687C136764020 @default.
- W2979746687 hasConceptScore W2979746687C144024400 @default.
- W2979746687 hasConceptScore W2979746687C154945302 @default.
- W2979746687 hasConceptScore W2979746687C15744967 @default.
- W2979746687 hasConceptScore W2979746687C169760540 @default.
- W2979746687 hasConceptScore W2979746687C17744445 @default.
- W2979746687 hasConceptScore W2979746687C180747234 @default.
- W2979746687 hasConceptScore W2979746687C199539241 @default.
- W2979746687 hasConceptScore W2979746687C2522767166 @default.
- W2979746687 hasConceptScore W2979746687C2776359362 @default.
- W2979746687 hasConceptScore W2979746687C2776674806 @default.
- W2979746687 hasConceptScore W2979746687C2776889888 @default.
- W2979746687 hasConceptScore W2979746687C2779304628 @default.
- W2979746687 hasConceptScore W2979746687C36289849 @default.
- W2979746687 hasConceptScore W2979746687C41008148 @default.
- W2979746687 hasConceptScore W2979746687C48856860 @default.
- W2979746687 hasConceptScore W2979746687C518677369 @default.
- W2979746687 hasConceptScore W2979746687C542102704 @default.
- W2979746687 hasConceptScore W2979746687C94625758 @default.
- W2979746687 hasIssue "125" @default.
- W2979746687 hasLocation W29797466871 @default.
- W2979746687 hasOpenAccess W2979746687 @default.
- W2979746687 hasPrimaryLocation W29797466871 @default.
- W2979746687 hasRelatedWork W2748952813 @default.
- W2979746687 hasRelatedWork W2899084033 @default.
- W2979746687 hasRelatedWork W2961085424 @default.
- W2979746687 hasRelatedWork W3046775127 @default.
- W2979746687 hasRelatedWork W3170094116 @default.
- W2979746687 hasRelatedWork W4285260836 @default.
- W2979746687 hasRelatedWork W4286629047 @default.
- W2979746687 hasRelatedWork W4306321456 @default.
- W2979746687 hasRelatedWork W4306674287 @default.
- W2979746687 hasRelatedWork W4224009465 @default.
- W2979746687 isParatext "false" @default.
- W2979746687 isRetracted "false" @default.
- W2979746687 magId "2979746687" @default.
- W2979746687 workType "article" @default.