網(wǎng)絡(luò)定向廣告投放算法研究.pdf

1、浙江大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院碩士學(xué)位論文網(wǎng)絡(luò)定向廣告投放算法研究姓名：俞淑平申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：計(jì)算機(jī)應(yīng)用技術(shù)指導(dǎo)教師：董金祥陳剛20100125浙江大學(xué)碩士學(xué)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