Skoči na glavni sadržaj

Pregledni rad

https://doi.org/10.19279/TVZ.PD.2021-9-3-02

SENTIMENT ANALYSIS TOOLS

Amelia Kovačević ; Nacionalna i sveučilišna knjižnica u Zagrebu, Zagreb, Hrvatska
Željko Kovačević orcid id orcid.org/0000-0003-2055-6877 ; Tehničko veleučilište u Zagrebu, Zagreb, Hrvatska


Puni tekst: hrvatski pdf 1.222 Kb

str. 167-174

preuzimanja: 430

citiraj


Sažetak

Sentiment analysis (or opinion mining) is a natural language processing technique used to determine whether data is positive, negative, or neutral. Given the exceptional importance of this technique in making business decisions that largely depend on the evaluation of the opinions of end users and customers, this paper provides an overview of several commonly used tools that can be used for these purposes. They use keywords to search certain Internet content such as social networks, forums, blogs and the like. Then, using built-in algorithms and keywords, they analyze sentiment and assign positive, negative, or neutral connotations. The paper deals with three topics of different categories. Their purpose is only to show the similarities and differences of the tools and the types of concepts that are analyzed. The purpose is not to provide a general analysis and judgment of the tools but to show by concrete examples how they work and what can be achieved by them in market opinion research

Ključne riječi

sentiment analysis; opinion mining; tools; evalation; social media; subjectivity

Hrčak ID:

273774

URI

https://hrcak.srce.hr/273774

Datum izdavanja:

10.11.2021.

Podaci na drugim jezicima: hrvatski

Posjeta: 1.563 *