• norsk
    • English
  • English 
    • norsk
    • English
  • Login
View Item 
  •   Home
  • Fakultet for teknologi, kunst og design (TKD)
  • TKD - Institutt for informasjonsteknologi
  • View Item
  •   Home
  • Fakultet for teknologi, kunst og design (TKD)
  • TKD - Institutt for informasjonsteknologi
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Improving classification of tweets using word-word co-occurrence information from a large external corpus

Hammer, Hugo Lewi; Yazidi, Anis; Bai, Aleksander; Engelstad, Paal E.
Chapter, Peer reviewed, Chapter
Accepted version
Thumbnail
View/Open
p1174-hammer.pdf (676.1Kb)
Co_location_final_V3.pdf (274.1Kb)
URI
https://hdl.handle.net/10642/3723
Date
2016
Metadata
Show full item record
Collections
  • TKD - Institutt for informasjonsteknologi [860]
Original version
Hammer HL, Yazidi A, Bai A, Engelstad P.E.: Improving classification of tweets using word-word co-occurrence information from a large external corpus. In: Ossowski S. Proceedings of the 31st Annual ACM Symposium on Applied Computing (SAC '16), 2016. Association for Computing Machinery (ACM) p. 1174-1177   http://dx.doi.org/10.1145/2851613.2851986
Abstract
Classifying tweets is an intrinsically hard task as tweets are

short messages which makes traditional bags of words based

approach ine cient. In fact, bags of words approaches ig-

nores relationships between important terms that do not

co-occur literally.

In this paper we resort to word-word co-occurence informa-

tion from a large corpus to expand the vocabulary of another

corpus consisting of tweets. Our results show that we are

able to reduce the number of erroneous classi cations by

14% using co-occurence information.
Publisher
Association for Computing Machinery (ACM)

Contact Us | Send Feedback

Privacy policy
DSpace software copyright © 2002-2019  DuraSpace

Service from  Unit
 

 

Browse

ArchiveCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDocument TypesJournalsThis CollectionBy Issue DateAuthorsTitlesSubjectsDocument TypesJournals

My Account

Login

Statistics

View Usage Statistics

Contact Us | Send Feedback

Privacy policy
DSpace software copyright © 2002-2019  DuraSpace

Service from  Unit