prikaz prve stranice dokumenta Model za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor
Access restricted to students and staff of home institution
master's thesis
Model za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor
2024. urn:nbn:hr:155:508165
Marušić, Hrvoje
University of Dubrovnik
Faculty of Electrical Engineering and Applied Computing

Cite this document

Marušić, H. (2024). Model za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor (Master's thesis). Dubrovnik: University of Dubrovnik. Retrieved from https://urn.nsk.hr/urn:nbn:hr:155:508165

Marušić, Hrvoje. "Model za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor." Master's thesis, University of Dubrovnik, 2024. https://urn.nsk.hr/urn:nbn:hr:155:508165

Marušić, Hrvoje. "Model za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor." Master's thesis, University of Dubrovnik, 2024. https://urn.nsk.hr/urn:nbn:hr:155:508165

Marušić, H. (2024). 'Model za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor', Master's thesis, University of Dubrovnik, accessed 17 November 2024, https://urn.nsk.hr/urn:nbn:hr:155:508165

Marušić H. Model za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor [Master's thesis]. Dubrovnik: University of Dubrovnik; 2024 [cited 2024 November 17] Available at: https://urn.nsk.hr/urn:nbn:hr:155:508165

H. Marušić, "Model za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor", Master's thesis, University of Dubrovnik, Dubrovnik, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:155:508165

Please login to the repository to save this object to your list.
Metadata
TitleModel za analizu sentimenta na temelju korisničkih iskustava o Dubrovniku s platforme Tripadvisor
Title (english)A SENTIMENT ANALYSIS MODEL BASED ON USER EXPERIENCES ABOUT DUBROVNIK ON THE TRIPADVISOR PLATFORM
AuthorHrvoje Marušić
MentorIvona Zakarija (mentor)
Committee memberAdriana Lipovac Vrhovac (predsjednik povjerenstva)
Committee memberIvona Zakarija (član povjerenstva)
Committee memberZorica Krželj Čolović (član povjerenstva)
GranterUniversity of Dubrovnik
(Faculty of Electrical Engineering and Applied Computing)
Dubrovnik
Defense date and country2024-05-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
Ovaj rad proučava kako posjetitelji doživljavaju grad Dubrovnik pomoću korisničkih iskustava objavljenih na platformi Tripadvisor. Prvi korak u istraživanju bio je implementiranje skripte za web struganje recenzija povezanih s turističkom atrakcijom „Old town“ s platforme Tripadvisor. Zatim je razvijen model za analizu sentimenta koristeći prethodno trenirani roBERTa model. Naposljetku, provedena je analiza sentimenta kako bi se usporedile recenzije napisane u 2022. i 2023. godini. Primjenom modela ostvareni su obećavajući rezultati koji su prikazani u završnom djelu rada. Ova se metoda može lako primijeniti na druge turističke atrakcije, pružajući donositeljima odluka mogućnost poboljšanja usluga, povećanja angažmana posjetitelja i postizanja većih profita.
Abstract (english)
This thesis examines how visitors experience Dubrovnik based on the reviews published on the Tripadvisor platform. The first step of the research consisted of implementing a web scraping script to retrieve reviews about the tourist attraction „Old Town“ from Tripadvisor. Then, a sentiment analysis model was developed using the pre-trained RoBERTa model. Finally, a sentiment analysis was conducted to compare reviews from 2022 and 2023. Promising results were obtained by applying the model, which are presented in the last part of the thesis. This method can be easily applied to other tourist attractions and offers decision-makers the opportunity to improve their services, increase visitor engagement and generate higher profits.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:155:508165
Study programmeTitle: /
Study programme type: university
Study level: graduate
Academic / professional title: sveučilišni/a magistar/magistra inženjer/inženjerka računarstva (sveučilišni/a magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2024-06-10 10:57:00