FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280515861> ?p ?o ?g. }

• W4280515861 abstract "Algorithms provide powerful tools for detecting and dissecting human bias and error. Here, we develop machine learning methods to to analyze how humans err in a particular high-stakes task: image interpretation. We leverage a unique dataset of 16,135,392 human predictions of whether a neighborhood voted for Donald Trump or Joe Biden in the 2020 US election, based on a Google Street View image. We show that by training a machine learning estimator of the Bayes optimal decision for each image, we can provide an actionable decomposition of human error into bias, variance, and noise terms, and further identify specific features (like pickup trucks) which lead humans astray. Our methods can be applied to ensure that human-in-the-loop decision-making is accurate and fair and are also applicable to black-box algorithmic systems." @default.
• W4280515861 created "2022-05-22" @default.
• W4280515861 creator A5065870025 @default.
• W4280515861 creator A5067807487 @default.
• W4280515861 creator A5072849579 @default.
• W4280515861 creator A5073415222 @default.
• W4280515861 creator A5081701167 @default.
• W4280515861 creator A5087471530 @default.
• W4280515861 date "2022-06-20" @default.
• W4280515861 modified "2023-09-26" @default.
• W4280515861 title "Trucks Don’t Mean Trump: Diagnosing Human Error in Image Analysis" @default.
• W4280515861 cites W1849277567 @default.
• W4280515861 cites W2033743788 @default.
• W4280515861 cites W2095932468 @default.
• W4280515861 cites W2108598243 @default.
• W4280515861 cites W2168199261 @default.
• W4280515861 cites W2590955327 @default.
• W4280515861 cites W2769358515 @default.
• W4280515861 cites W2796402109 @default.
• W4280515861 cites W2950068534 @default.
• W4280515861 cites W2962859337 @default.
• W4280515861 cites W2963834345 @default.
• W4280515861 cites W2979893369 @default.
• W4280515861 cites W2998401461 @default.
• W4280515861 cites W3003162384 @default.
• W4280515861 cites W3004390862 @default.
• W4280515861 cites W3012624518 @default.
• W4280515861 cites W3014888349 @default.
• W4280515861 cites W3032243264 @default.
• W4280515861 cites W3033620876 @default.
• W4280515861 cites W3033733989 @default.
• W4280515861 cites W3034854469 @default.
• W4280515861 cites W3046215811 @default.
• W4280515861 cites W3101206394 @default.
• W4280515861 cites W3121044953 @default.
• W4280515861 cites W3121654114 @default.
• W4280515861 cites W3125892916 @default.
• W4280515861 cites W3134395196 @default.
• W4280515861 cites W3156579229 @default.
• W4280515861 cites W3209972423 @default.
• W4280515861 cites W4233995128 @default.
• W4280515861 cites W4249247059 @default.
• W4280515861 cites W4288086175 @default.
• W4280515861 doi "https://doi.org/10.1145/3531146.3533145" @default.
• W4280515861 hasPublicationYear "2022" @default.
• W4280515861 type Work @default.
• W4280515861 citedByCount "0" @default.
• W4280515861 crossrefType "proceedings-article" @default.
• W4280515861 hasAuthorship W4280515861A5065870025 @default.
• W4280515861 hasAuthorship W4280515861A5067807487 @default.
• W4280515861 hasAuthorship W4280515861A5072849579 @default.
• W4280515861 hasAuthorship W4280515861A5073415222 @default.
• W4280515861 hasAuthorship W4280515861A5081701167 @default.
• W4280515861 hasAuthorship W4280515861A5087471530 @default.
• W4280515861 hasBestOaLocation W42805158611 @default.
• W4280515861 hasConcept C105795698 @default.
• W4280515861 hasConcept C115961682 @default.
• W4280515861 hasConcept C119857082 @default.
• W4280515861 hasConcept C121955636 @default.
• W4280515861 hasConcept C127413603 @default.
• W4280515861 hasConcept C144133560 @default.
• W4280515861 hasConcept C146978453 @default.
• W4280515861 hasConcept C153083717 @default.
• W4280515861 hasConcept C154945302 @default.
• W4280515861 hasConcept C169806903 @default.
• W4280515861 hasConcept C185429906 @default.
• W4280515861 hasConcept C196083921 @default.
• W4280515861 hasConcept C33923547 @default.
• W4280515861 hasConcept C41008148 @default.
• W4280515861 hasConcept C52121051 @default.
• W4280515861 hasConcept C99498987 @default.
• W4280515861 hasConceptScore W4280515861C105795698 @default.
• W4280515861 hasConceptScore W4280515861C115961682 @default.
• W4280515861 hasConceptScore W4280515861C119857082 @default.
• W4280515861 hasConceptScore W4280515861C121955636 @default.
• W4280515861 hasConceptScore W4280515861C127413603 @default.
• W4280515861 hasConceptScore W4280515861C144133560 @default.
• W4280515861 hasConceptScore W4280515861C146978453 @default.
• W4280515861 hasConceptScore W4280515861C153083717 @default.
• W4280515861 hasConceptScore W4280515861C154945302 @default.
• W4280515861 hasConceptScore W4280515861C169806903 @default.
• W4280515861 hasConceptScore W4280515861C185429906 @default.
• W4280515861 hasConceptScore W4280515861C196083921 @default.
• W4280515861 hasConceptScore W4280515861C33923547 @default.
• W4280515861 hasConceptScore W4280515861C41008148 @default.
• W4280515861 hasConceptScore W4280515861C52121051 @default.
• W4280515861 hasConceptScore W4280515861C99498987 @default.
• W4280515861 hasFunder F4320332180 @default.
• W4280515861 hasLocation W42805158611 @default.
• W4280515861 hasLocation W42805158612 @default.
• W4280515861 hasOpenAccess W4280515861 @default.
• W4280515861 hasPrimaryLocation W42805158611 @default.
• W4280515861 hasRelatedWork W2054803721 @default.
• W4280515861 hasRelatedWork W2899439164 @default.
• W4280515861 hasRelatedWork W2950038056 @default.
• W4280515861 hasRelatedWork W2961085424 @default.
• W4280515861 hasRelatedWork W2973057117 @default.
• W4280515861 hasRelatedWork W3124716596 @default.
• W4280515861 hasRelatedWork W4286629047 @default.
• W4280515861 hasRelatedWork W4306674287 @default.

• next