Litcius/Paper detail

WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover’s Distance in Sociocultural Analysis

Mikael Brunila, Jack LaViolette

202121 citationsDOIOpen Access PDF

Abstract

Despite the increasing popularity of NLP in the humanities and social sciences, advances in model performance and complexity have been accompanied by concerns about interpretability and explanatory power for sociocultural analysis.

Topics & Concepts

InterpretabilityComputer scienceNatural language processingPopularityArtificial intelligenceSociocultural evolutionSet (abstract data type)Word (group theory)Social mediaExtrapolationContext (archaeology)Classifier (UML)Sentiment analysisLinguisticsData scienceWorld Wide WebMathematicsSociologyStatisticsPaleontologySocial psychologyPhilosophyBiologyProgramming languageAnthropologyPsychologyTopic ModelingComputational and Text Analysis MethodsMisinformation and Its Impacts
WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover’s Distance in Sociocultural Analysis | Litcius