Analiza sentimenta iz korisničkih recenzija ugostiteljskih objekata

undergraduate thesis

• Title (english): Sentiment Analysis from Customer Reviews of Hospitality and Catering Businesses
• Author: Roman Kerčmar
• Mentor: Jan Šnajder (mentor)
• Committee member: Jan Šnajder (predsjednik povjerenstva)
• Committee member: Mladen Karan (član povjerenstva)
• Committee member: Domagoj Alagić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Analiza sentimenta iz korisničkih recenzija teži predvidjeti korisničku ocjenu isključivo na temelju teksta. Ispitane su dvije arhitekture neuronskih mreža, Konvolucijske i dvosmjerne povratne mreže. Učene su kao regresijski i kao klasifikacijski modeli. Dvosmjerne povratne mreže u kombinaciji s LSTM ćelijom pokazale su se najbolje i prema Pearsonovom koeficijentu korelacije (0.842) i prema točnosti (0.65).

Abstract (english)

Sentiment analysis from customer reviews aims to predict user grade by looking only at the text of the review. We examine two architectures of neural networks, convolutional and bidirectional neural networks. Models are trained as regression models and as classifiers. Bidirectional neural networks with LSTM as the base cell have shown to be the best with highest Pearson's correlation coefficient (0.842) and accuracy (0.65).

• Keywords: Obrada prirodnog jezika; strojno učenje; duboko učenje; analiza sentimenta; konvolucijska neuronska mreža; dvosmjerna povratna neuronska mreža; ćelija s dugoročnom memorijom; engleski jezik
• Keywords (english): Natural language processing; machine learning; deep learning; sentiment analysis; convolutional neural network; bidirectional neural network; long short-term memory unit; English language
• Language: croatian
• URN:NBN: urn:nbn:hr:168:318602
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 21:30:37