網絡定向廣告投放算法研究.pdf

1、浙江大學計算機科學與技術學院碩士學位論文網絡定向廣告投放算法研究姓名：俞淑平申請學位級別：碩士專業(yè)：計算機應用技術指導教師：董金祥陳剛20100125浙江大學碩士學位論文AbstractAbstractWiththerapiddevelopmentoftheInteractadvertisingindustry，targetedadvertisingasanewnetworkadvertisingmodelisalsodevelopin

2、gveryquicklyThiskindofadvertisingisveryattractivebecauseit’Saccurate，timelyandefficientTargetedadvertisingisakindofadvertisingwhichisdeliveredonwebpageswiththepagecontentoruserbehaviorrelatedTargetedadvertisingcanbedivid

3、edintocontenttargetedadvertisingandbehavioraltargetingadvertisingaccordingtothedifferenttargetsForthecontenttargetedadvertising，wepresentanefficientsemantic—basedcontenttargetedadvertisingalgorithmThisalgorithmfirstofall

4、usesthesemanticrelationsbetweenwordstoexpandwebpagekeywordsandcalculatestheweightsoftheseexpandedwordswiththehelpofApproximateBayesianWeightComputingModel，thencomputesthesimilaritiesbetweenexpandedwebpagesandadsusingtheI

5、mprovedVectorSpaceModelAtlastwesortadsaccordingtothesesimilaritiesandfindproperadsforwebpagesForthebehavioraltargetingadvertising，weproposeanewbehavioraltargetingadvertisingalgorithmwhichisbasedontheuserbehaviorfeaturean

6、alysisThealgorithmfirstofallclusterstheusers’recentlyvisitedwebpagesaccordingtotheUserBehaviorFeatureModel，thenanalyzeseachclusterofwebpagesusingtheUserBehaviorFeatureAnalysisAlgorithmandcalculatesitsweightaccordinglyWit

7、hthisweightandthesimilaritybetweentheclustercenterandads，wecancalculatethefinalscoresofadsAtlastwesortadsaccordingtotheirscoresandfindproperadsfortheusersAlargenumberofexperimentsshowthatthesetwoalgorithmsareveryeffectiv

8、etargetedadvertisingalgorithmswhichCanmatchadsandthewebpagecontentoruserbehavioreffectivelyandhaveaverybrightfutureKeywords：Contenttargetedadvertising，Behavioraltargetingadvertising，Vectorspacemodel，Semantic，Userbehavior