using evidence based content trust model for spam detection

using evidence based content trust model for spam detection

ID:7524408

大小:430.81 KB

页数:8页

时间:2018-02-17

using evidence based content trust model for spam detection_第1页
using evidence based content trust model for spam detection_第2页
using evidence based content trust model for spam detection_第3页
using evidence based content trust model for spam detection_第4页
using evidence based content trust model for spam detection_第5页
资源描述:

《using evidence based content trust model for spam detection》由会员上传分享,免费在线阅读,更多相关内容在工程资料-天天文库

1、ExpertSystemswithApplications37(2010)5599–5606ContentslistsavailableatScienceDirectExpertSystemswithApplicationsjournalhomepage:www.elsevier.com/locate/eswaUsingevidencebasedcontenttrustmodelforspamdetectiona,b,ca,b,cd,*WeiWang,GuosunZeng,DaizhongTangaDepartmentofComputerScienceandEng

2、ineering,TongjiUniversity,Shanghai200092,ChinabTongjiBranchNationalEngineeringandTechnologyCenterofHighPerformance,Shanghai200092,ChinacKeyLaboratoryofEmbeddedSystemandServiceComputing,MinistryofEducation,Shanghai200092,ChinadSchoolofEconomicsandManagement,TongjiUniversity,Shanghai200

3、092,ChinaarticleinfoabstractKeywords:Contenttrustisoneofthemaincomponentsintheresearchofinformationretrieval.AsitgetseasiertoContenttrustaddinformationtotheWebviaHTMLpages,wikis,blogs,andotherdocuments,itgetstoughertodistin-Webspamguishaccurateortrustworthyinformationfrominaccurateoru

4、ntrustworthyinformationontheWeb.RankingCurrenttechnologyofspamdetectionisbasedonbinarymetric,thatisbinaryclassificationisadaptedSVMinthespamdetection.Inordertomeettheusers’needandpreference,moreaccuratemetricisneededMachinelearninginthecontenttrustaswellasindetectingspaminformation.Int

5、hispaper,weusethenotionofcontenttrustforspamdetection,andregarditasarankingproblem.Besidestraditionaltextfeatureattributes,informationqualitybasedevidenceisintroducedtodefinethetrustfeatureofspaminformation,andanovelcontenttrustlearningalgorithmbasedontheseevidenceisproposed.Finally,aW

6、ebspamdetec-tionsystemisdevelopedandtheexperimentsontherealWebdataarecarriedout,whichshowthepro-posedmethodperformsverywellinpractice.Ó2010ElsevierLtd.Allrightsreserved.1.Introductiontratingsearchexperiences.Second,ifausersearchesforinforma-tionthatisrelevanttoyourpagesbutyourpagesare

7、rankedlowInformationretrieval(IR)isthestudyofhelpinguserstofindbysearchengines,thentheusermaynotseethepagesbecauseinformationthatmatchestheirinformationneeds.Technically,oneseldomclicksalargenumberofreturnedpages.Finally,ainformationretrievalstudiestheacquisition,organization,storage,s

8、earch

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。