{"title":"Leveraging Temporal Markers to Detect Event from Microblogs","authors":"Soumaya Cherichi, R. Faiz","doi":"10.4018/IJKSR.2017070104","DOIUrl":null,"url":null,"abstract":"Oneofthemarvelsofourtimeistheunprecedenteddevelopmentanduseoftechnologiesthatsupport socialinteraction.Socialmediatingtechnologieshaveengenderedradicallynewwaysofinformation andcommunication,particularlyduringevents;incaseofnaturaldisasterlikeearthquakestsunami andAmericanpresidentialelection.ThispaperisbasedondataobtainedfromTwitterbecauseof itspopularityandsheerdatavolume.Thiscontentcanbecombinedandprocessedtodetectevents, entitiesandpopularmoodstofeedvariousnewlarge-scaledata-analysisapplications.Onthedownside, thesecontentitemsareverynoisyandhighlyinformal,makingitdifficulttoextractsenseoutofthe stream.Takingtoaccountallthedifficulties,weproposeaneweventdetectionapproachcombining linguisticfeaturesandTwitterfeatures.Finally,wepresentoursystemthataims(1)detectnewevents, (2)torecognizetemporalmarkerspatternofanevent,(3)andtoclassifyimportanteventsaccording tothematicpertinence,authorpertinenceandtweetvolume. KEywoRDS Clustering, Event Detection, Microblogs, NLP, Patterns, Social Network Analysis, Temporal Markers, Twitter","PeriodicalId":296518,"journal":{"name":"Int. J. Knowl. Soc. Res.","volume":"101 10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Knowl. Soc. Res.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/IJKSR.2017070104","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
利用时间标记从微博中检测事件
Oneofthemarvelsofourtimeistheunprecedenteddevelopmentanduseoftechnologiesthatsupport socialinteraction。Socialmediatingtechnologieshaveengenderedradicallynewwaysofinformation andcommunication,particularlyduringevents;incaseofnaturaldisasterlikeearthquakestsunami andAmericanpresidentialelection。ThispaperisbasedondataobtainedfromTwitterbecauseof itspopularityandsheerdatavolume。Thiscontentcanbecombinedandprocessedtodetectevents, entitiesandpopularmoodstofeedvariousnewlarge-scaledata-analysisapplications。Onthedownside, thesecontentitemsareverynoisyandhighlyinformal,makingitdifficulttoextractsenseoutofthe流。Takingtoaccountallthedifficulties,weproposeaneweventdetectionapproachcombining linguisticfeaturesandTwitterfeatures.Finally,wepresentoursystemthataims(1)detectnewevents, (2)torecognizetemporalmarkerspatternofanevent, (3)andtoclassifyimportanteventsaccording tothematicpertinence,authorpertinenceandtweetvolume。关键词聚类,事件检测,微博,自然语言处理,模式,社会网络分析,时间标记,推特
本文章由计算机程序翻译,如有差异,请以英文原文为准。