Actively Predicting Diverse Search Intent from User Browsing Behaviors

Actively Predicting Diverse Search Intent from User Browsing Behaviors

ID:40047394

大小:669.60 KB

页数:10页

时间:2019-07-18

Actively Predicting Diverse Search Intent from User Browsing Behaviors_第1页
Actively Predicting Diverse Search Intent from User Browsing Behaviors_第2页
Actively Predicting Diverse Search Intent from User Browsing Behaviors_第3页
Actively Predicting Diverse Search Intent from User Browsing Behaviors_第4页
Actively Predicting Diverse Search Intent from User Browsing Behaviors_第5页
资源描述:

《Actively Predicting Diverse Search Intent from User Browsing Behaviors》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、WWW2010•FullPaperApril26-30•Raleigh•NC•USAActivelyPredictingDiverseSearchIntentfromUser∗BrowsingBehaviorsZhicongChengBinGaoTie-YanLiuSchoolofSoftwareandMicrosoftResearchAsiaMicrosoftResearchAsiaMicroelectronics4F,SigmaCenter,No.49,4F,SigmaCenter,No.49,PekingUniversityZhichunRoadZhichun

2、RoadBeijing,100871,P.R.ChinaBeijing,100190,P.R.ChinaBeijing,100190,P.R.Chinaczc0316@live.combingao@microsoft.comtyliu@microsoft.comABSTRACT1.INTRODUCTIONThispaperisconcernedwithactivelypredictingsearchin-UserintentunderstandinghasbecomeahottopicinWebtentfromuserbrowsingbehaviordata.Inr

3、ecentyears,greatsearchanddatamining,andcommercialsearchengineshaveattentionhasbeenpaidtopredictingusersearchintent.realizeditsimportanceforprovidingbettersearchexperi-1However,thepredictionwasmostlypassivebecauseitwasences.Forexample,Google,Yahoo!,Bing,andAskallperformedonlyafteruserss

4、ubmittedtheirqueriestosearchprovidequerysuggestion[1,3,13]asapredictionofuserengines.Itisnotconsideredwhyusersissuedthesequeries,searchintent.Whilesuchatechniquehasachievedcertainandwhattriggeredtheirinformationneeds.Accordingtosuccess,italsohasobviouslimitations,someofwhichareourstudy

5、,manyinformationneedsofuserswereactuallylistedasbelow.triggeredbywhattheyhavebrowsed.Thatis,afterread-•Thepredictionwasconductedinapassivemanner,ingapage,ifauserfoundsomethinginterestingorunclear,inthesensethatitwasperformedonlyafterusershe/shemighthavetheintenttoobtainfurtherinformati

6、onsubmittedtheirqueriestosearchengines.Notethatandaccordinglyformulateasearchquery.Activelypredict-Webusersspendmostoftheirtimenotonsearch,butingsuchsearchintentcanbenefitbothsearchenginesandinsteadonbrowsing,authoring,andsoon.Thereforetheirusers.Inthispaper,weproposeaseriesoftechnologi

7、esinmostcases,whenusershavelatentsearchintents,tofulfillthistask.First,weextractallthequeriesthatuserssearchenginescannotmakemeaningfulpredictions.Inissuedafterreadingagivenpagefromuserbrowsingbehav-thisregard,theimpactofpassiveintentpredictiononiordata.Second,welearnamodeltoeffectivel

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。