Contextual preference mining for user profile construction

Contextual preference mining for user profile construction

ID:40711842

大小:1.80 MB

页数:18页

时间:2019-08-06

Contextual preference mining for user profile construction_第1页
Contextual preference mining for user profile construction_第2页
Contextual preference mining for user profile construction_第3页
Contextual preference mining for user profile construction_第4页
Contextual preference mining for user profile construction_第5页
资源描述:

《Contextual preference mining for user profile construction》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、InformationSystems49(2015)182–199ContentslistsavailableatScienceDirectInformationSystemsjournalhomepage:www.elsevier.com/locate/infosys$Contextualpreferenceminingforuserprofileconstructionab,ccSandradeAmo,MouhamadouSaliouDiallo,CheikhTalibouyaDiop,bbbArnaudGiacometti,DominiqueLi,A

2、rnaudSouletaUniversidadeFederaldeUberlândia,Av.JoãoNavesdeAvila212138400-902Uberlândia,MG,BrazilbUniversitéFrançoisRabelaisdeTours,3PlaceJeanJaurès41029Blois,FrancecUniversitéGastonBerger,BP234,Saint-Louis,SenegalarticleinfoabstractArticlehistory:Theemergingofubiquitouscomputingte

3、chnologiesinrecentyearshasgivenrisetoaReceived5February2014newfieldofresearchconsistinginincorporatingcontext-awarepreferencequeryingReceivedinrevisedformfacilitiesindatabasesystems.OneimportantstepinthissettingisthePreferenceElicitation13November2014taskwhichconsistsinprovidingth

4、euserwaystoinformhis/herchoiceonpairsofobjectsAccepted22November2014withaminimaleffort.InthispaperweproposeanautomaticpreferenceelicitationRecommendedby:F.KornAvailableonline3December2014methodbasedonminingtechniques.Themethodconsistsinextractingauserprofilefromasetofuserpreferenc

5、esamples.Inoursetting,aprofileisspecifiedbyasetofcontextualKeywords:preferencerulesverifyingpropertiesofsoundnessandconciseness.AfterprovingthatthePatternminingproblemisNP-complete,weproposearesolutionin2phases.ThefirstphaseextractsallPreferenceelicitationindividualuserpreferences

6、bymeansofcontextualpreferencerules.ThesecondphaseContextualpreferencerulebuildstheuserprofilestartingfromthiscollectionofrulesusingagreedymethod.ToUserprofileminingassessthequalityofuserprofiles,weproposethreerankingtechniquesbenefitingfromtheseprofilesthatenableustorankobjectsacc

7、ordingtouserpreferences.Weevaluatetheefficacyofourthreerankingstrategiesandcomparethemwithawell-knownrankingmethod(SVMRANK).Theevaluationiscarriedoutthroughanextensivesetofexperimentsexecutedonareal-worlddatabaseofuserpreferencesaboutmovies.&2014ElsevierLtd.Allrightsreserved.1.Int

8、roductionessentialinthesystemmode

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。