Show simple item record

dc.contributor.authorAppel, Orestesen
dc.contributor.authorChiclana, Franciscoen
dc.contributor.authorCarter, Jennyen
dc.contributor.authorFujita, Hamidoen
dc.date.accessioned2016-04-11T15:01:15Z
dc.date.available2016-04-11T15:01:15Z
dc.date.issued2016
dc.identifier.citationAppel, O. et al. (2016) A Hybrid Approach to Sentiment Analysis with Benchmarking Results. Accepted for presentation at IEA/AIE-2016.en
dc.identifier.urihttp://hdl.handle.net/2086/11859
dc.description.abstractThe objective of this article is two-fold. Firstly, a hybrid approach to Sentiment Analysis encompassing the use of Semantic Rules, Fuzzy Sets and an enriched Sentiment Lexicon, improved with the support of SentiWordNet is described. Secondly, the proposed hybrid method is compared against two well established Supervised Learning techniques, Naïve Bayes and Maximum Entropy. Using the well known and publicly available Movie Review Dataset, the proposed hybrid system achieved higher accuracy and precision than Naïve Bayes (NB) and Maximum Entropy (ME).en
dc.language.isoenen
dc.publisherSpringer Lectures Notes Computer Scienceen
dc.subjectSentiment Analysisen
dc.subjectFuzzy Setsen
dc.subjectSemantic Rulesen
dc.subjectNatural Language Processingen
dc.subjectComputational Linguisticen
dc.subjectSentiWordNeten
dc.titleA Hybrid Approach to Sentiment Analysis with Benchmarking Resultsen
dc.typeConferenceen
dc.researchgroupCentre for Computational Intelligenceen
dc.peerreviewedYesen
dc.funderNAen
dc.projectidNAen
dc.cclicenceCC-BY-NCen
dc.researchinstituteInstitute of Artificial Intelligence (IAI)en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record