{"?xml":{"@version":"1.0"},"edm:RDF":{"@xmlns:dc":"http://purl.org/dc/elements/1.1/","@xmlns:edm":"http://www.europeana.eu/schemas/edm/","@xmlns:wgs84_pos":"http://www.w3.org/2003/01/geo/wgs84_pos","@xmlns:foaf":"http://xmlns.com/foaf/0.1/","@xmlns:rdaGr2":"http://rdvocab.info/ElementsGr2","@xmlns:oai":"http://www.openarchives.org/OAI/2.0/","@xmlns:owl":"http://www.w3.org/2002/07/owl#","@xmlns:rdf":"http://www.w3.org/1999/02/22-rdf-syntax-ns#","@xmlns:ore":"http://www.openarchives.org/ore/terms/","@xmlns:skos":"http://www.w3.org/2004/02/skos/core#","@xmlns:dcterms":"http://purl.org/dc/terms/","edm:WebResource":[{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:doc-6BTAKLZ4/efafc9ab-4752-4be3-bade-31b5cd922bf3/PDF","dcterms:extent":"317 KB"},{"@rdf:about":"http://www.dlib.si/stream/URN:NBN:SI:doc-6BTAKLZ4/ce1cf376-06e6-48da-a0ca-926a43ea6868/TEXT","dcterms:extent":"58 KB"}],"edm:TimeSpan":{"@rdf:about":"2013-2025","edm:begin":{"@xml:lang":"en","#text":"2013"},"edm:end":{"@xml:lang":"en","#text":"2025"}},"edm:ProvidedCHO":{"@rdf:about":"URN:NBN:SI:doc-6BTAKLZ4","dcterms:isPartOf":[{"@rdf:resource":"https://www.dlib.si/details/URN:NBN:SI:spr-BR18JCH2"},{"@xml:lang":"sl","#text":"Slovenščina 2.0"}],"dcterms:issued":"2023","dc:creator":["Čibej, Jaka","Dobrovoljc, Kaja","Kosem, Iztok","Kuzman, Taja","Ljubešić, Nikola"],"dc:format":[{"@xml:lang":"sl","#text":"številka:1"},{"@xml:lang":"sl","#text":"letnik:11"},{"@xml:lang":"sl","#text":"str. 161-188"}],"dc:identifier":["DOI:10.4312/slo2.0.2023.1.161-188","COBISSID_HOST:173943811","ISSN:2335-2736","URN:URN:NBN:SI:doc-6BTAKLZ4"],"dc:language":"sl","dc:publisher":{"@xml:lang":"sl","#text":"Založba Univerze v Ljubljani"},"dc:subject":[{"@xml:lang":"en","#text":"automatic text categorization"},{"@xml:lang":"sl","#text":"avtomatska kategorizacija besedil"},{"@xml:lang":"sl","#text":"Korpusi (jezikoslovje)"},{"@xml:lang":"en","#text":"monitor corpus"},{"@xml:lang":"en","#text":"neologisms"},{"@xml:lang":"sl","#text":"neologizmi"},{"@xml:lang":"en","#text":"news sites"},{"@xml:lang":"sl","#text":"novičarski portali"},{"@xml:lang":"sl","#text":"Obdelava naravnega jezika (računalništvo)"},{"@xml:lang":"sl","#text":"Računalniško jezikoslovje"},{"@xml:lang":"en","#text":"Slovene"},{"@xml:lang":"sl","#text":"Slovenščina"},{"@xml:lang":"sl","#text":"spremljevalni korpus"}],"dcterms:temporal":{"@rdf:resource":"2013-2025"},"dc:title":{"@xml:lang":"sl","#text":"Spremljevalni korpus Trendi in avtomatska kategorizacija|"},"dc:description":[{"@xml:lang":"sl","#text":"The paper presents the compilation of the Trendi corpus, the first monitor cor-pus of Slovene. The current version (Trendi 2023-02) contains texts published between January 2019 and October 2023, with a total of over 700 million tokens (more than 586 million words). The purpose of the corpus is to provide linguists and non-linguists with data on current language use and to enable the monitoring of new words as well as the increase and decline in the use of existing words. In the paper, we present the contents of the corpus and the methods and criteria used in its compilation. The second part of the paper is focused on the development of a tool for categorizing text topics in news articles. The tool was developed specifically for the Trendi corpus but can be used for other corpora containing similar texts. A set of 13 thematic categories was developed for the tool. The set generally follows international standards and categories used in comparable corpora for other languages. Using texts annotated with these categories, we trained multiple language models and achieved a high classification accuracy when categorizing text topics"},{"@xml:lang":"sl","#text":"Prispevek predstavlja izdelavo korpusa Trendi, prvega spremljevalnega korpusa za slovenščino. Trenutna različica Trendi 2023-02 pokriva besedila od januarja 2019 do konca februarja 2023, vsebuje pa že več kot 700 milijonov pojavnic oz. več kot 586 milijonov besed. Namen korpusa je, da tako strokovni kot nestrokovni javnosti ponudi podatke o aktualni jezikovni rabi in omogoči spremljanje pojavljanja novih besed ter upadanja ali naraščanja rabe že obstoječih. Poleg same vsebine predstavimo tudi metodologijo in načela izdelave korpusa. Drugi del prispevka opisuje razvoj algoritma za avtomatsko kategorizacijo besedil z novičarskih portalov, ki je bil pripravljen za potrebe korpusa Trendi in tudi drugih korpusov s tovrstnimi besedili. Za namene algoritma je bil izdelan nabor 13 tematskih kategorij, ki so v veliki meri prekrivne z mednarodnimi standardi in kategorijami v primerljivih korpusih drugih jezikov. Na besedilih, označenih s kategorijami, smo naučili več različnih jezikovnih modelov in z najprimernejšim dosegli visoko zanesljivost določevanja tematike besedilom"}],"edm:type":"TEXT","dc:type":[{"@xml:lang":"sl","#text":"znanstveno časopisje"},{"@xml:lang":"en","#text":"journals"},{"@rdf:resource":"http://www.wikidata.org/entity/Q361785"}]},"ore:Aggregation":{"@rdf:about":"http://www.dlib.si/?URN=URN:NBN:SI:doc-6BTAKLZ4","edm:aggregatedCHO":{"@rdf:resource":"URN:NBN:SI:doc-6BTAKLZ4"},"edm:isShownBy":{"@rdf:resource":"http://www.dlib.si/stream/URN:NBN:SI:doc-6BTAKLZ4/efafc9ab-4752-4be3-bade-31b5cd922bf3/PDF"},"edm:rights":{"@rdf:resource":"http://creativecommons.org/licenses/by-sa/4.0/"},"edm:provider":"Slovenian National E-content Aggregator","edm:intermediateProvider":{"@xml:lang":"en","#text":"National and University Library of Slovenia"},"edm:dataProvider":{"@xml:lang":"sl","#text":"Univerza v Ljubljani, Filozofska fakulteta"},"edm:object":{"@rdf:resource":"http://www.dlib.si/streamdb/URN:NBN:SI:doc-6BTAKLZ4/maxi/edm"},"edm:isShownAt":{"@rdf:resource":"http://www.dlib.si/details/URN:NBN:SI:doc-6BTAKLZ4"}}}}