Inverted Polarity Bigram Lexicons

datacite.relation.isSupplementTo https://doi.org/10.18653/v1/W15-2911
dc.contributor.author Flekova, Lucie
dc.contributor.author Ruppert, Eugen
dc.contributor.author Preotiuc-Pietro, Daniel
dc.date.accessioned 2020-07-25T09:14:02Z
dc.date.available 2020-07-25T09:14:02Z
dc.date.created 2015
dc.date.issued 2020-07-25
dc.description Sentiment prediction from Twitter is of the utmost interest for research and commercial organizations. Systems are usually using lexicons, where each word is positive or negative. However, word lexicons suffer from ambiguities at a contextual level: the word dark is positive in dark chocolate and negative in dark soul, the word lost is positive with weight and so on. We introduce a method which helps to identify frequent contexts in which a word switches polarity, and to reveal which words often appear in both positive and negative contexts. We show that our method matches human perception of polarity and demonstrate improvements in automated sentiment classification. Our method also helps to assess the suitability to use an existing lexicon to a new platform (e.g. Twitter). en_US
dc.identifier.uri https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/2450
dc.language.iso en en_US
dc.rights.licenseCC-BY-4.0 (https://creativecommons.org/licenses/by/4.0)
dc.subject.classification 4.43-04
dc.subject.classification 4.43-05
dc.subject.ddc 004
dc.title Inverted Polarity Bigram Lexicons en_US
dc.type Dataset en_US
dcterms.accessRights openAccess
person.identifier.orcid #PLACEHOLDER_PARENT_METADATA_VALUE#
person.identifier.orcid #PLACEHOLDER_PARENT_METADATA_VALUE#
person.identifier.orcid #PLACEHOLDER_PARENT_METADATA_VALUE#
tuda.history.classification Version=2016-2020;409-05 Interaktive und intelligente Systeme, Bild- und Sprachverarbeitung, Computergraphik und Visualisierung
tuda.project Bund/BMBF | 01IS12054 | SC_Flekova

Files

Original bundle

Now showing 1 - 1 of 1
NameDescriptionSizeFormat
wassa_inverted_polarity.zip115.86 KBZIP-Archivdateien Download