Automatic Categorisation of Croatian Web Sites (CROSBI ID 513816)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Dobša, Jasminka ; Radošević, Danijel ; Stapić, Zlatko ; Zubac, Marinko
engleski
Automatic Categorisation of Croatian Web Sites
On the Web site www.hr we can find the catalogue of Croatian Web sites organized hierarchically in more then 600 categories. So far new Web sites have been added into the hierarchy manually. The aim of our work was to research the possibilities of automatic categorisation of Croatian Web sites in the hierarcy of catalogue. For the representation of documents (Web sites) we have used text mining technique of bag of words representation, while for purpose of categorisation we have used the technique of support vector machines. The experiments are conducted for categorisation of Web sites in 14 categories on the highes hierarchical level.
automatic classification; Croatian Web sites; text mining; bag of words representation; support vector machines
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
144-149-x.
2005.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of 25th International Convention MIPRO 2005
Budin, Leo ; Ribarić, Slobodan
Rijeka: Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO
Podaci o skupu
25th International Convention MIPRO 2005
predavanje
30.05.2005-03.06.2005
Opatija, Hrvatska