基于用户-分析的个性化微博推荐技术-研究

基于用户-分析的个性化微博推荐技术-研究

ID:27375284

大小:956.50 KB

页数:88页

时间:2018-12-03

基于用户-分析的个性化微博推荐技术-研究_第1页
基于用户-分析的个性化微博推荐技术-研究_第2页
基于用户-分析的个性化微博推荐技术-研究_第3页
基于用户-分析的个性化微博推荐技术-研究_第4页
基于用户-分析的个性化微博推荐技术-研究_第5页
资源描述:

《基于用户-分析的个性化微博推荐技术-研究》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、...基于用户分析的个性化微博推荐技术研究AbstractAsatypicalrepresentativeofthesocialnetwork,microbloghasattractedalargenumber ofusersbyit’sfacilitatecommunication,spreadrapidlyandinteractivity.Withthegrowthof userscale,informationinmicroblogalsoshowsexplosivegrowth.Largeamountof informationleadstotheinformationove

2、rloadinmicroblog.Informationoverloadbrings manyproblemstousers,oneofthemisthatwiththenumberoffriendsthatuserfollowed increased,thedailyinformationpushedtousersisalsoincreased.Microblogusersare overwhelmedwithmostlyuninterestingpiecesoftextinordertoaccessinformationofvalue. Howtopickouttheconten

3、tsthatusersareinterestedfromalargenumberofmicroblog informationisthekeytosolvetheinformationoverloadinmicroblog.Toprovidethepersonalizedrecommendationserviceformicroblogusers,firstly,we mustknowwhyusersshowgreatinterestonthismicrobloginformation.Thereasonsmaybe aretherelationshipbetweenusers,th

4、einfluenceofinformationpublisherorthesimilarityof interestbetweentheuserandthetopicofmicrobloginformation.Inthisthesis,weconvertthe microblogrecommendationintoasortproblemontheinformationstreamthatuserreceived. Thelearntorankmethodisusedtolearnthesortfunctionontrainingdata,thenweusethe function

5、tocalculatetherelevancescorethatrepresentativetherelevancebetweenmicroblog informationanduserpreference.Therecommendationlistisgivenbyadescendingsequence ofmicrobloginformationinusersession.Theresearchcontentsofthispaperareasfollows: (1)Inordertoquantifytheuser’scharacteristicsthatcanembodyuser

6、’spersonalized demand,weanalysistheexistingresearchmethodsandthenselectproperfeature representationmethods.(2)Westudyonthemethodtopartitionuser’ssession.Sinceourpurposeisto recommendtheusersrecentlyreceivedinformation,wehavetofindoutwhatinformationthe userreceivesintherecentvisit.Weuseanapproxi

7、matemethodtodefineausersessionbased onusers’observableactivitiessuchaspublishing,replying.(3)Therelativerelevanceassumptionisintroducedtoconstructthetrainingdata.By analyzingusers’actioninmicroblog,weusetherelativerelevanceassumpt

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。