Naslov
Building a Sentiment Dictionary for Croatian

Autori
Ban Kirigin, Tajana ; Bujačić Babić, Sanda ; Perak, Benedikt

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
Book of Abstracts LAP 2021 / - , 2021, 67-68

Skup
Logic and Applications 2021

Mjesto i datum
Dubrovnik, Hrvatska, 20.09.2021. - 24.09.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
lexical graph analysis ; corpus ; affective computing ; sentiment analysis ; sentiment dictionary

Sažetak
The work presented in this paper aims to provide the research community with a set of sentiment lexicons constructed by expanding existing sentiment dictionary resources for Croatian. Our corpus-based syntactic dependency graph approach to sentiment value propagation led us to release automatically generated sentiment lexicons. This interdisciplinary dictionary expansion method is structured around the ConGraCNet lexical graph, which enables the assignment of sentiment values to a single lexical item or the computation of sentiment values for missing lexemes or entire lexical communities by propagating the values from an existing sentiment dictionary. We present the computational methods and resources used for dictionary expansion as well as the description of the final sentiment dictionary resource.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Računarstvo, Filologija

POVEZANOST RADA