prikaz prve stranice dokumenta Analiza sentimenata u korisničkim recenzijama online turističkih agencija
Access restricted to authenticated users
master's thesis
Analiza sentimenata u korisničkim recenzijama online turističkih agencija
2022. urn:nbn:hr:179:356463
Štribić, Andriana
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Štribić, A. (2022). Analiza sentimenata u korisničkim recenzijama online turističkih agencija (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:356463

Štribić, Andriana. "Analiza sentimenata u korisničkim recenzijama online turističkih agencija." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:356463

Štribić, Andriana. "Analiza sentimenata u korisničkim recenzijama online turističkih agencija." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:356463

Štribić, A. (2022). 'Analiza sentimenata u korisničkim recenzijama online turističkih agencija', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 26 April 2024, https://urn.nsk.hr/urn:nbn:hr:179:356463

Štribić A. Analiza sentimenata u korisničkim recenzijama online turističkih agencija [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 April 26] Available at: https://urn.nsk.hr/urn:nbn:hr:179:356463

A. Štribić, "Analiza sentimenata u korisničkim recenzijama online turističkih agencija", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:356463

Please login to the repository to save this object to your list.
Metadata
TitleAnaliza sentimenata u korisničkim recenzijama online turističkih agencija
Title (english)Analysis of sentiments in user reviews of online tourist agencies
AuthorAndriana Štribić
MentorMladen Russo https://orcid.org/0000-0002-9363-6723 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-22, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad je proučavao analizu sentimenta u kontekstu primjene metoda umjetne inteligencije na primjera recenzija s internera. Opisani su pojmovi koji predstavljaju osnovni temelj računalne analize sentimenta, a to su umjetna inteligencija, strojno učenje i rudarenje podataka. Osim samog pojma analize sentimenta, definirane su i razine. Nakon toga, obrađeni su primjeri korištenja računalne analize sentimenta u praksi te su pomoću tih primjera opisane prepreke s kojima se programeri susreću i njihova potencijalna rješenja. Opisane su dvije vrste sustava za računalnu analizu sentimenta: sustav temeljen na pravilima i automatski sustav. Za dotične sustave opisane su metode kojima su oni realizirani i utvrđene njihove prednosti i mane. Praktični dio rada uključuje primjenu naivnog Bayesovog klasifikatora za „treniranje“ programa za analizu sentimenta i evaluaciju istog tog programa na postojećim recenzijama s internetskih stranica.
Abstract (english)
This work studied sentiment analysis in the context of applying artificial intelligence methods to examples of internal reviews. The concepts that represent the basic foundation of computer sentiment analysis are described - artificial intelligence, machine learning and data mining. In addition to the very concept of sentiment analysis, levels are also defined. After that, examples of the use of computer sentiment analysis in practice were processed, and with the help of these examples, obstacles faced by programmers and their potential solutions were described. Two types of computerized sentiment analysis systems are described: a rule-based system and an automatic system. For the systems in question, the methods by which they were realized and their advantages and disadvantages were determined. The practical part of the work includes the application of a Naive Bayes classifier for "training" a program for sentiment analysis and evaluating the same program on existing reviews from internet sites.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:356463
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-07-07 12:04:28