Pregled bibliografske jedinice broj: 788174
Toward Network-based Keyword Extraction from Multitopic Web Documents
Toward Network-based Keyword Extraction from Multitopic Web Documents // Social sciences via network analysis and computation / Kanduč, Tadej (ur.).
Frankfurt : Berlin : Bern : Bruxelles : New York (NY) : Oxford : Beč: Peter Lang, 2015. str. 39-52
CROSBI ID: 788174 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Toward Network-based Keyword Extraction from Multitopic Web Documents
Autori
Šišović, Sabina ; Martinčić-Ipšić, Sanda ; Meštrović, Ana
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
Social sciences via network analysis and computation
Urednik/ci
Kanduč, Tadej
Izdavač
Peter Lang
Grad
Frankfurt : Berlin : Bern : Bruxelles : New York (NY) : Oxford : Beč
Godina
2015
Raspon stranica
39-52
ISBN
978-3-631-66522-0
Ključne riječi
keyword extraction, complex networks, co-occurrence language networks, Croatian texts, selectivity
Sažetak
In this paper we analyse the selectivity measure calculated from the complex network in the task of the automatic keyword extraction. Texts, collected from different web sources (portals, forums), are represented as directed and weighted co-occurrence complex networks of words. Words are nodes and links are established between two nodes if they are directly co-occurring within a sentence. We test different centrality measures for ranking nodes - keyword candidates. The promising results are achieved using the selectivity measure. Then we propose an approach which enables extracting word pairs according to the values of the in/out-selectivity and weight measures combined with filtering.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti
POVEZANOST RADA
Projekti:
Uniri LangNet
Ustanove:
Fakultet informatike i digitalnih tehnologija, Rijeka