Improving sentiment analysis through ensemble learning of meta-level features

Simple item page
dc.contributor.authorAlnashwan, Rana
dc.contributor.authorO'Riordan, Adrian P.
dc.contributor.authorSorensen, Humphrey
dc.contributor.authorHoare, Cathal
dc.date.accessioned2017-05-16T10:53:37Z
dc.date.available2017-05-16T10:53:37Z
dc.date.issued2016-09
dc.date.updated2017-05-16T10:29:40Z
dc.description.abstractIn this research, the well-known microblogging site, Twitter, was used for a sentiment analysis investigation. We propose an ensemble learning approach based on the meta-level features of seven existing lexicon resources for automated polarity sentiment classification. The ensemble employs four base learners (a Two-Class Support Vector Machine, a Two-Class Bayes Point Machine, a Two-Class Logistic Regression and a Two-Class Decision Forest) for the classification task. Three different labelled Twitter datasets were used to evaluate the effectiveness of this approach to sentiment analysis. Our experiment shows that, based on a combination of existing lexicon resources, the ensemble learners minimize the error rate by avoiding poor selection from stand-alone classifiers.en
dc.description.statusPeer revieweden
dc.description.urihttp://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=51953en
dc.description.versionPublished Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationAlnashwan, R., O’Riordan, A., Sorensen, H. and Hoare, C. (2016) ‘Improving sentiment analysis through ensemble learning of meta-level features’ (from the Proceedings of the 2nd International Workshop on Knowledge Discovery on the WEB, Cagliari, Italy, 8 – 10 September), CEUR Workshop Proceedings, 1748.en
dc.identifier.issn1613-0073
dc.identifier.journaltitleCEUR Workshop Proceedingsen
dc.identifier.urihttps://hdl.handle.net/10468/3972
dc.identifier.volume1748en
dc.language.isoenen
dc.publisherSun SITE Central Europe (CEUR) / RWTH Aachen Universityen
dc.relation.ispartofKDWEB 2016 : 2nd International Workshop on Knowledge Discovery on the Web
dc.relation.urihttp://ceur-ws.org/Vol-1748/
dc.rights© 2016, the Authors.en
dc.rights.urihttp://ceur-ws.org/
dc.subjectOpinion miningen
dc.subjectSentiment analysisen
dc.subjectLexiconen
dc.subjectMachine learningen
dc.subjectTwitteren
dc.titleImproving sentiment analysis through ensemble learning of meta-level featuresen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2619.pdf
Size:
566.06 KB
Format:
Adobe Portable Document Format
Description:
Published Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Conference Items