Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217764315> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3217764315 abstract "Sociodemographic biases are a common problem for natural language processing, affecting the fairness and integrity of its applications. Within sentiment analysis, these biases may undermine sentiment predictions for texts that mention personal attributes that unbiased human readers would consider neutral. Such discrimination can have great consequences in the applications of sentiment analysis both in the public and private sectors. For example, incorrect inferences in applications like online abuse and opinion analysis in social media platforms can lead to unwanted ramifications, such as wrongful censoring, towards certain populations. In this paper, we address the discrimination against people with disabilities, PWD, done by sentiment analysis and toxicity classification models. We provide an examination of sentiment and toxicity analysis models to understand in detail how they discriminate PWD. We present the Bias Identification Test in Sentiments (BITS), a corpus of 1,126 sentences designed to probe sentiment analysis models for biases in disability. We use this corpus to demonstrate statistically significant biases in four widely used sentiment analysis tools (TextBlob, VADER, Google Cloud Natural Language API and DistilBERT) and two toxicity analysis models trained to predict toxic comments on Jigsaw challenges (Toxic comment classification and Unintended Bias in Toxic comments). The results show that all exhibit strong negative biases on sentences that mention disability. We publicly release BITS Corpus for others to identify potential biases against disability in any sentiment analysis tools and also to update the corpus to be used as a test for other sociodemographic variables as well." @default.
- W3217764315 created "2021-12-06" @default.
- W3217764315 creator A5029933077 @default.
- W3217764315 creator A5056978982 @default.
- W3217764315 date "2021-11-25" @default.
- W3217764315 modified "2023-09-27" @default.
- W3217764315 title "Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models" @default.
- W3217764315 cites W1979539500 @default.
- W3217764315 cites W2019759670 @default.
- W3217764315 cites W2033702744 @default.
- W3217764315 cites W2097726431 @default.
- W3217764315 cites W2099813784 @default.
- W3217764315 cites W2134576123 @default.
- W3217764315 cites W2471350540 @default.
- W3217764315 cites W2483215953 @default.
- W3217764315 cites W2573660794 @default.
- W3217764315 cites W2596598033 @default.
- W3217764315 cites W2600084544 @default.
- W3217764315 cites W2604821579 @default.
- W3217764315 cites W2760255222 @default.
- W3217764315 cites W2794607770 @default.
- W3217764315 cites W2795975316 @default.
- W3217764315 cites W2802105481 @default.
- W3217764315 cites W2805744755 @default.
- W3217764315 cites W2893425640 @default.
- W3217764315 cites W2895651111 @default.
- W3217764315 cites W2903284953 @default.
- W3217764315 cites W2949678053 @default.
- W3217764315 cites W2962990575 @default.
- W3217764315 cites W2963341956 @default.
- W3217764315 cites W2971307358 @default.
- W3217764315 cites W2972413484 @default.
- W3217764315 cites W2976959554 @default.
- W3217764315 cites W2978017171 @default.
- W3217764315 cites W2978849696 @default.
- W3217764315 cites W2988128310 @default.
- W3217764315 cites W2991618856 @default.
- W3217764315 cites W3009306974 @default.
- W3217764315 cites W3034282334 @default.
- W3217764315 cites W3034951181 @default.
- W3217764315 cites W3035296331 @default.
- W3217764315 cites W3083434198 @default.
- W3217764315 cites W3125099730 @default.
- W3217764315 cites W3134678353 @default.
- W3217764315 hasPublicationYear "2021" @default.
- W3217764315 type Work @default.
- W3217764315 sameAs 3217764315 @default.
- W3217764315 citedByCount "0" @default.
- W3217764315 crossrefType "posted-content" @default.
- W3217764315 hasAuthorship W3217764315A5029933077 @default.
- W3217764315 hasAuthorship W3217764315A5056978982 @default.
- W3217764315 hasConcept C11192451 @default.
- W3217764315 hasConcept C116834253 @default.
- W3217764315 hasConcept C154945302 @default.
- W3217764315 hasConcept C204321447 @default.
- W3217764315 hasConcept C2522767166 @default.
- W3217764315 hasConcept C41008148 @default.
- W3217764315 hasConcept C59822182 @default.
- W3217764315 hasConcept C66402592 @default.
- W3217764315 hasConcept C86803240 @default.
- W3217764315 hasConceptScore W3217764315C11192451 @default.
- W3217764315 hasConceptScore W3217764315C116834253 @default.
- W3217764315 hasConceptScore W3217764315C154945302 @default.
- W3217764315 hasConceptScore W3217764315C204321447 @default.
- W3217764315 hasConceptScore W3217764315C2522767166 @default.
- W3217764315 hasConceptScore W3217764315C41008148 @default.
- W3217764315 hasConceptScore W3217764315C59822182 @default.
- W3217764315 hasConceptScore W3217764315C66402592 @default.
- W3217764315 hasConceptScore W3217764315C86803240 @default.
- W3217764315 hasLocation W32177643151 @default.
- W3217764315 hasOpenAccess W3217764315 @default.
- W3217764315 hasPrimaryLocation W32177643151 @default.
- W3217764315 isParatext "false" @default.
- W3217764315 isRetracted "false" @default.
- W3217764315 magId "3217764315" @default.
- W3217764315 workType "article" @default.