Novelty detection for topic tracking

Simple item page
dc.citation.epage795en_US
dc.citation.issueNumber4en_US
dc.citation.spage777en_US
dc.citation.volumeNumber63en_US
dc.contributor.authorAksoy, C.en_US
dc.contributor.authorCan, F.en_US
dc.contributor.authorKocberber, S.en_US
dc.date.accessioned2016-02-08T09:47:40Z
dc.date.available2016-02-08T09:47:40Z
dc.date.issued2012en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractMultisource web news portals provide various advantages such as richness in news content and an opportunity to follow developments from different perspectives. However, in such environments, news variety and quantity can have an overwhelming effect. New-event detection and topic-tracking studies address this problem. They examine news streams and organize stories according to their events; however, several tracking stories of an event/topic may contain no new information (i.e., no novelty). We study the novelty detection (ND) problem on the tracking news of a particular topic. For this purpose, we build a Turkish ND test collection called BilNov-2005 and propose the usage of three ND methods: a cosine-similarity (CS)-based method, a language-model (LM)-based method, and a cover-coefficient (CC)-based method. For the LM-based ND method, we show that a simpler smoothing approach, Dirichlet smoothing, can have similar performance to a more complex smoothing approach, Shrinkage smoothing. We introduce a baseline that shows the performance of a system with random novelty decisions. In addition, a category-based threshold learning method is used for the first time in ND literature. The experimental results show that the LM-based ND method significantly outperforms the CS- and CC-based methods, and categorybased threshold learning achieves promising results when compared to general threshold learning. © 2011 ASIS&T.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T09:47:40Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2012en
dc.identifier.doi10.1002/asi.21697en_US
dc.identifier.issn2330-1635
dc.identifier.urihttp://hdl.handle.net/11693/21530
dc.language.isoEnglishen_US
dc.publisherJohn Wiley & Sons, Inc.en_US
dc.relation.isversionofhttp://dx.doi.org/10.1002/asi.21697en_US
dc.source.titleAssociation for Information Science and Technology. Journalen_US
dc.subjectDirichleten_US
dc.subjectMultisourcesen_US
dc.subjectNews contenten_US
dc.subjectNovelty detectionen_US
dc.subjectTest collectionen_US
dc.subjectThreshold learningen_US
dc.subjectTopic trackingen_US
dc.subjectTurkishsen_US
dc.subjectInformation servicesen_US
dc.subjectInformation retrieval systemsen_US
dc.titleNovelty detection for topic trackingen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Novelty detection for topic tracking.pdf
Size:
351.82 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Scholarly Publications - Computer Engineering