Bootstrapping Websites for Classification of Organization Names on Twitter

Bootstrapping Websites for Classification of Organization Names on Twitter

ID:40049776

大小:60.48 KB

页数:6页

时间:2019-07-18

Bootstrapping Websites for Classification of Organization Names on Twitter_第1页
Bootstrapping Websites for Classification of Organization Names on Twitter_第2页
Bootstrapping Websites for Classification of Organization Names on Twitter_第3页
Bootstrapping Websites for Classification of Organization Names on Twitter_第4页
Bootstrapping Websites for Classification of Organization Names on Twitter_第5页
资源描述:

《Bootstrapping Websites for Classification of Organization Names on Twitter》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、BootstrappingWebsitesforClassificationofOrganizationNamesonTwitterPaulKalmarKalmarResearchpaul@KalmarResearch.comAbstract.Therehasbeenagrowinginterestinmonitoringthesocialmediapresenceofcompaniesforimprovedmarketing.ManypublicAPIsareavailablefortappingintothe

2、data,andtherearecompaniesthatwillcollectallpostsrelatedtoagivensetofkeywords.Butwithsomuchdata,whoistosaythatallofthepostsarerelevant,especiallywhensomanycompanyandproductnamesarehighlyambiguous?InthecontextoftheWePSTask2,weaimtoreducenoisebycollectingonlythe

3、relevanttweetsaboutacompanygiventhecompany'swebsiteandsetofTwitterdata.Inarealworldsituation,anycompanywhowantedtoidentifytweetsaboutthemselvescouldprovideashortlistoflabeledtweetsandusethisasabasesetfortrainingdata.Giventhatforthistaskweweregivenalargelistof

4、companieswithnosuchtrainingdata,itwouldhavebeenunrealistictocreatesuchdataforeachcompany.Wechosetousethecompany'swebsiteassurrogatetrainingdata.BecausethewebsitescomefromadifferentregisterthanTwitter,weusedtheinitialmodeltobootstrapamodelfromtheactualtweets.A

5、sitisthemostsimpledatatoacquire,thefeatureswechosetouseweretheco-occurringwordsineachtweet.Tocomputetherelevanceofeachwordtoagivencompany,wecomputedthepointwisemutualinformationbetweenthewordandthetarget'slabel.Theresultsshowthatourapproachwassuccessful,yetwi

6、throomforimprovement.Keywords:bootstrap,unsupervised,Twitter,disambiguation1IntroductionTherehasbeenagrowinginterestinmonitoringthesocialmediapresenceofcompaniesforimprovedmarketing.ManypublicAPIsareavailablefortappingintothedata,andtherearecompaniesthatwillc

7、ollectallpostsrelatedtoagivensetofkeywords.Butwithsomuchdata,whoistosaythatallofthepostsarerelevant,especiallywhensomanycompanyandproductnamesarehighlyambiguous?InthecontextoftheWePSTask2,weaimtoreducenoisebycollectingonlytherelevanttweetsaboutacompanygiventh

8、ecompany'swebsiteandsetofTwitterdata.2MethodForthetaskofclassification,thereneedstobeatleastonewelldefinedclass.Inarealworldsituation,anycompanywhowantedtoidentifytweetsaboutthemselvescou

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。