Full metadata record
DC FieldValueLanguage
dc.contributor.authorGrolmus, Petr
dc.date.accessioned2016-06-24T07:21:26Z
dc.date.available2016-06-24T07:21:26Z
dc.date.issued2004
dc.identifier.urihttp://www.kiv.zcu.cz/publications/
dc.identifier.urihttp://hdl.handle.net/11025/21604
dc.format39 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherUniversity of West Bohemia in Pilsenen
dc.rights© University of West Bohemia in Pilsenen
dc.subjectvyhledávánícs
dc.subjectuživatelský profilcs
dc.subjectalgoritmuscs
dc.titleUser profile detection based on text mining: technical report no. DCSE/TR-2004-09en
dc.typezprávacs
dc.typereporten
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedThe old-fashioned search engine model based usually on Boole´s algebra has become outdated. Current systems tend to meet users (customers) needs more precisely and hence they have to improve their basis. The searching process has to be based on deeper knowledge of individual user preferences - i.e. on user profiles. This work presents an overview of recommender and expert finding systems. It also introduces the ProGen System rising at the University of West Bohemia. For the characteristic phrases selection from document collections is used the STC algorithm. Our system is able to work with multi-lingual document collections. A developed document language recognition is based on stop-word occurrence. We have developed a stemming algorithm combining both the dictionary-based and algorithm-based method. Finally, an outlook for the future work is sketched out.en
dc.subject.translatedsearchingen
dc.subject.translateduser profileen
dc.subject.translatedalgorithmen
Appears in Collections:Zprávy / Reports (KIV)

Files in This Item:
File Description SizeFormat 
Grolmus.pdfPlný text506,16 kBAdobe PDFView/Open


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/21604

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.