Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386273236> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4386273236 abstract "Ranking schemes drive many real-world decisions, like, where to study, whom to hire, what to buy, etc. Many of these decisions often come with high consequences. For example, a university can be deemed less prestigious if not featured in a top-k list, and consumers might not even explore products that do not get recommended to buyers. At the heart of most of these decisions are opaque ranking schemes, which dictate the ordering of data entities, but their internal logic is inaccessible or proprietary. Drawing inferences about the ranking differences is like a guessing game to the stakeholders, like, the rankees (i.e., the entities who are ranked, like product companies) and the decision-makers (i.e., who use the rankings, like buyers). In this paper, we aim to enable transparency in ranking interpretation by using algorithmic rankers that learn from available data and by enabling human reasoning about the learned ranking differences using explainable AI (XAI) methods. To realize this aim, we leverage the exploration-explanation paradigm of human-data interaction to let human stakeholders explore subsets and groupings of complex multi-attribute ranking data using visual explanations of model fit and attribute influence on rankings. We realize this explanation paradigm for transparent ranking interpretation in TRIVEA, a visual analytic system that is fueled by: i) visualizations of model fit derived from algorithmic rankers that learn the associations between attributes and rankings from available data and ii) visual explanations derived from XAI methods that help abstract important patterns, like, the relative influence of attributes in different ranking ranges. Using TRIVEA, end users not trained in data science have the agency to transparently reason about the global and local behavior of the rankings without the need to open black-box ranking models and develop confidence in the resulting attribute-based inferences. We demonstrate the efficacy of TRIVEA using multiple usage scenarios and subjective feedback from researchers with diverse domain expertise. Keywords: Visual Analytics, Learning-to-Rank, Explainable ML, Ranking" @default.
- W4386273236 created "2023-08-31" @default.
- W4386273236 creator A5019202280 @default.
- W4386273236 creator A5043572697 @default.
- W4386273236 creator A5051193196 @default.
- W4386273236 creator A5079138298 @default.
- W4386273236 date "2023-08-28" @default.
- W4386273236 modified "2023-09-27" @default.
- W4386273236 title "TRIVEA: Transparent Ranking Interpretation using Visual Explanation of Black-Box Algorithmic Rankers" @default.
- W4386273236 doi "https://doi.org/10.48550/arxiv.2308.14622" @default.
- W4386273236 hasPublicationYear "2023" @default.
- W4386273236 type Work @default.
- W4386273236 citedByCount "0" @default.
- W4386273236 crossrefType "posted-content" @default.
- W4386273236 hasAuthorship W4386273236A5019202280 @default.
- W4386273236 hasAuthorship W4386273236A5043572697 @default.
- W4386273236 hasAuthorship W4386273236A5051193196 @default.
- W4386273236 hasAuthorship W4386273236A5079138298 @default.
- W4386273236 hasBestOaLocation W43862732361 @default.
- W4386273236 hasConcept C119857082 @default.
- W4386273236 hasConcept C153083717 @default.
- W4386273236 hasConcept C154945302 @default.
- W4386273236 hasConcept C189430467 @default.
- W4386273236 hasConcept C199360897 @default.
- W4386273236 hasConcept C23123220 @default.
- W4386273236 hasConcept C2522767166 @default.
- W4386273236 hasConcept C2780233690 @default.
- W4386273236 hasConcept C38652104 @default.
- W4386273236 hasConcept C41008148 @default.
- W4386273236 hasConcept C527412718 @default.
- W4386273236 hasConceptScore W4386273236C119857082 @default.
- W4386273236 hasConceptScore W4386273236C153083717 @default.
- W4386273236 hasConceptScore W4386273236C154945302 @default.
- W4386273236 hasConceptScore W4386273236C189430467 @default.
- W4386273236 hasConceptScore W4386273236C199360897 @default.
- W4386273236 hasConceptScore W4386273236C23123220 @default.
- W4386273236 hasConceptScore W4386273236C2522767166 @default.
- W4386273236 hasConceptScore W4386273236C2780233690 @default.
- W4386273236 hasConceptScore W4386273236C38652104 @default.
- W4386273236 hasConceptScore W4386273236C41008148 @default.
- W4386273236 hasConceptScore W4386273236C527412718 @default.
- W4386273236 hasLocation W43862732361 @default.
- W4386273236 hasOpenAccess W4386273236 @default.
- W4386273236 hasPrimaryLocation W43862732361 @default.
- W4386273236 hasRelatedWork W2118564381 @default.
- W4386273236 hasRelatedWork W2283927842 @default.
- W4386273236 hasRelatedWork W2357241418 @default.
- W4386273236 hasRelatedWork W2961085424 @default.
- W4386273236 hasRelatedWork W3194506168 @default.
- W4386273236 hasRelatedWork W4286629047 @default.
- W4386273236 hasRelatedWork W4306321456 @default.
- W4386273236 hasRelatedWork W4306674287 @default.
- W4386273236 hasRelatedWork W4376855027 @default.
- W4386273236 hasRelatedWork W4224009465 @default.
- W4386273236 isParatext "false" @default.
- W4386273236 isRetracted "false" @default.
- W4386273236 workType "article" @default.