Lexicon-basedSentiment lexicon GitHubSentiment analysis dictionarysentiment lexicon meaningSentiment polarityTextBlob polaritySentiment lexiconLexicon-based methods for sentiment analysisLexicon enhanced sentiment analysis framework using rule based classification schemeSentiment analysisTwitter sentiment analysis: lexicon method, machine learning method and their combinationAfinn

Improved lexicon-based sentiment analysis ... - Ulster University

文章推薦指數： 80 %
投票人數：10人

The algorithm consists of two key compo- nents, namely sentiment normalisation and evidence-based combination function, which have been used in ... Skiptomainnavigation Skiptosearch Skiptomaincontent Improvedlexicon-basedsentimentanalysisforsocialmediaanalytics AnnaJurek,MauriceMulvenna,YaxinBi SchoolofComputingFacultyOfComputing,Eng.&BuiltEnv. Researchoutput:Contributiontojournal›Article›peer-review 15 Downloads (Pure) Overview Fingerprint Abstract Socialmediachannels,suchasFacebookorTwitter,allowforpeopletoexpresstheirviewsandopinionsaboutanypublictopics.Publicsentimentrelatedtofutureevents,suchasdemonstrationsorparades,indicatepublicatti-tudeandthereforemaybeappliedwhiletryingtoestimatethelevelofdisruptionanddisorderduringsuchevents.Consequently,sentimentanalysisofsocialmediacontentmaybeofinterestfordierentorganisations,especiallyinsecurityandlawenforcementsectors.Thispaperpresentsanewlexicon-basedsentimentanalysisalgorithmthathasbeendesignedwiththemainfocusonrealtimeTwittercontentanalysis.Thealgorithmconsistsoftwokeycompo-nents,namelysentimentnormalisationandevidence-basedcombinationfunction,whichhavebeenusedinordertoestimatetheintensityofthesentimentratherthanpositive/negativelabelandtosupportthemixedsentimentclassicationprocess.Finally,weillustrateacasestudyexaminingtherelationbetweennegativesentimentoftwitterpostsrelatedtoEnglishDefenceLeagueandthelevelofdisorderduringtheorganisation’srelatedevents. OriginallanguageEnglishPages(from-to)1-13Numberofpages13JournalSecurityInformaticsVolume4Issuenumber9DOIshttps://doi.org/10.1186/s13388-015-0024-xPublicationstatusPublished-9Dec2015 KeywordsSentimentanalysisSocialmediaSecurity AccesstoDocument 10.1186/s13388-015-0024-xLicence:CCBYMulvenna-s13388-015-0024-xFinalpublishedversion,3.48MBLicence:CCBY Otherfilesandlinks PUREPORTALLINKLinktopublicationinSecurityInformatics Sentimentanalysis Engineering&MaterialsScience 100% Positiveions Engineering&MaterialsScience 55% Lawenforcement Engineering&MaterialsScience 50% Demonstrations Engineering&MaterialsScience 36% Citethis APA Author BIBTEX Harvard Standard RIS Vancouver Jurek,A.,Mulvenna,M.,&Bi,Y.(2015).Improvedlexicon-basedsentimentanalysisforsocialmediaanalytics.SecurityInformatics,4(9),1-13.https://doi.org/10.1186/s13388-015-0024-x Jurek,Anna;Mulvenna,Maurice;Bi,Yaxin./Improvedlexicon-basedsentimentanalysisforsocialmediaanalytics.In:SecurityInformatics.2015;Vol.4,No.9.pp.1-13. @article{4026fbb194a54e5e90b084bc1790e275,title="Improvedlexicon-basedsentimentanalysisforsocialmediaanalytics",abstract="Socialmediachannels,suchasFacebookorTwitter,allowforpeopletoexpresstheirviewsandopinionsaboutanypublictopics.Publicsentimentrelatedtofutureevents,suchasdemonstrationsorparades,indicatepublicatti-tudeandthereforemaybeappliedwhiletryingtoestimatethelevelofdisruptionanddisorderduringsuchevents.Consequently,sentimentanalysisofsocialmediacontentmaybeofinterestfordierentorganisations,especiallyinsecurityandlawenforcementsectors.Thispaperpresentsanewlexicon-basedsentimentanalysisalgorithmthathasbeendesignedwiththemainfocusonrealtimeTwittercontentanalysis.Thealgorithmconsistsoftwokeycompo-nents,namelysentimentnormalisationandevidence-basedcombinationfunction,whichhavebeenusedinordertoestimatetheintensityofthesentimentratherthanpositive/negativelabelandtosupportthemixedsentimentclassicationprocess.Finally,weillustrateacasestudyexaminingtherelationbetweennegativesentimentoftwitterpostsrelatedtoEnglishDefenceLeagueandthelevelofdisorderduringtheorganisation{\textquoteright}srelatedevents.",keywords="Sentimentanalysis,Socialmedia,Security",author="AnnaJurekandMauriceMulvennaandYaxinBi",year="2015",month=dec,day="9",doi="10.1186/s13388-015-0024-x",language="English",volume="4",pages="1--13",journal="SecurityInformatics",issn="2190-8532",publisher="Springer",number="9",} Jurek,A,Mulvenna,M&Bi,Y2015,'Improvedlexicon-basedsentimentanalysisforsocialmediaanalytics',SecurityInformatics,vol.4,no.9,pp.1-13.https://doi.org/10.1186/s13388-015-0024-x Improvedlexicon-basedsentimentanalysisforsocialmediaanalytics./Jurek,Anna;Mulvenna,Maurice;Bi,Yaxin.In:SecurityInformatics,Vol.4,No.9,09.12.2015,p.1-13.Researchoutput:Contributiontojournal›Article›peer-review TY-JOURT1-Improvedlexicon-basedsentimentanalysisforsocialmediaanalyticsAU-Jurek,AnnaAU-Mulvenna,MauriceAU-Bi,YaxinPY-2015/12/9Y1-2015/12/9N2-Socialmediachannels,suchasFacebookorTwitter,allowforpeopletoexpresstheirviewsandopinionsaboutanypublictopics.Publicsentimentrelatedtofutureevents,suchasdemonstrationsorparades,indicatepublicatti-tudeandthereforemaybeappliedwhiletryingtoestimatethelevelofdisruptionanddisorderduringsuchevents.Consequently,sentimentanalysisofsocialmediacontentmaybeofinterestfordierentorganisations,especiallyinsecurityandlawenforcementsectors.Thispaperpresentsanewlexicon-basedsentimentanalysisalgorithmthathasbeendesignedwiththemainfocusonrealtimeTwittercontentanalysis.Thealgorithmconsistsoftwokeycompo-nents,namelysentimentnormalisationandevidence-basedcombinationfunction,whichhavebeenusedinordertoestimatetheintensityofthesentimentratherthanpositive/negativelabelandtosupportthemixedsentimentclassicationprocess.Finally,weillustrateacasestudyexaminingtherelationbetweennegativesentimentoftwitterpostsrelatedtoEnglishDefenceLeagueandthelevelofdisorderduringtheorganisation’srelatedevents.AB-Socialmediachannels,suchasFacebookorTwitter,allowforpeopletoexpresstheirviewsandopinionsaboutanypublictopics.Publicsentimentrelatedtofutureevents,suchasdemonstrationsorparades,indicatepublicatti-tudeandthereforemaybeappliedwhiletryingtoestimatethelevelofdisruptionanddisorderduringsuchevents.Consequently,sentimentanalysisofsocialmediacontentmaybeofinterestfordierentorganisations,especiallyinsecurityandlawenforcementsectors.Thispaperpresentsanewlexicon-basedsentimentanalysisalgorithmthathasbeendesignedwiththemainfocusonrealtimeTwittercontentanalysis.Thealgorithmconsistsoftwokeycompo-nents,namelysentimentnormalisationandevidence-basedcombinationfunction,whichhavebeenusedinordertoestimatetheintensityofthesentimentratherthanpositive/negativelabelandtosupportthemixedsentimentclassicationprocess.Finally,weillustrateacasestudyexaminingtherelationbetweennegativesentimentoftwitterpostsrelatedtoEnglishDefenceLeagueandthelevelofdisorderduringtheorganisation’srelatedevents.KW-SentimentanalysisKW-SocialmediaKW-SecurityUR-https://pure.ulster.ac.uk/en/publications/improved-lexicon-based-sentiment-analysis-for-social-media-analyt-3UR-http://www.security-informatics.com/content/pdf/s13388-015-0024-x.pdfU2-10.1186/s13388-015-0024-xDO-10.1186/s13388-015-0024-xM3-ArticleVL-4SP-1EP-13JO-SecurityInformaticsJF-SecurityInformaticsSN-2190-8532IS-9ER- JurekA,MulvennaM,BiY.Improvedlexicon-basedsentimentanalysisforsocialmediaanalytics.SecurityInformatics.2015Dec9;4(9):1-13.https://doi.org/10.1186/s13388-015-0024-x

請為這篇文章評分？

延伸文章資訊