| Autor: |
Ban Kirigin, Tajana, Bujačić Babić, Sanda, Perak, Benedikt |
| Jazyk: |
angličtina |
| Rok vydání: |
2021 |
| Předmět: |
|
| Popis: |
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. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
