Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks
K. Mei, Sonia Fereidooni, Aylin Caliskan
Abstract
Warning: The content of this paper may be upsetting or triggering.
Topics & Concepts
Scale (ratio)PsychologySocioeconomic statusSentiment analysisNatural language processingCognitive psychologyArtificial intelligenceComputer scienceMachine learningSocial psychologyMedicinePopulationQuantum mechanicsPhysicsEnvironmental healthInterpreting and Communication in HealthcareMigration, Health and Trauma