Show simple item record

dc.contributor.authorTonkin, Emma
dc.contributor.authorTourte, Gregory J. L.
dc.contributor.authorZollers, Alla
dc.contributor.editorLussky, Joanen_US
dc.date.accessioned2008-10-20T00:00:01Z
dc.date.available2010-06-18T23:34:35Z
dc.date.issued2008en_US
dc.date.submitted2008-10-20en_US
dc.identifier.citationPerformance tags -- who's running the show? 2008,en_US
dc.identifier.urihttp://hdl.handle.net/10150/105795
dc.description.abstractWe describe a pilot study which specifically examines the prevalence and characteristics of performance tags on several sites. Identifying post-coordination of tags as a useful step in the study of this phenomenon, as well as other approaches to leveraging tags based on text and/or sentiment analysis, we demonstrate an approach to automation of this process, postcoordinating (segmenting) terms by means of a probabilistic model based around Markov chains. The effectiveness of this approach to parsing is evaluated with respect to the wide range of constructions visible on various services. Several candidate approaches for the latter stages of automated classification are identified.
dc.format.mimetypedocen_US
dc.language.isoenen_US
dc.subjectClassificationen_US
dc.subject.otherSocial taggingen_US
dc.subject.otherIndexing consistencyen_US
dc.subject.otherPost-coordinationen_US
dc.subject.otherAffecten_US
dc.titlePerformance tags -- who's running the show?en_US
dc.typeConference Paperen_US
html.description.abstractWe describe a pilot study which specifically examines the prevalence and characteristics of performance tags on several sites. Identifying post-coordination of tags as a useful step in the study of this phenomenon, as well as other approaches to leveraging tags based on text and/or sentiment analysis, we demonstrate an approach to automation of this process, postcoordinating (segmenting) terms by means of a probabilistic model based around Markov chains. The effectiveness of this approach to parsing is evaluated with respect to the wide range of constructions visible on various services. Several candidate approaches for the latter stages of automated classification are identified.


Files in this item

Thumbnail
Name:
Tonkin__SIG-CR-2008-final.doc
Size:
274.5Kb
Format:
Microsoft Word

This item appears in the following Collection(s)

Show simple item record