Modeli dubokog učenja za analizu korisničkih komentara na društvenim mrežama

master's thesis

• Title (english): Deep Learning Models for the Analysis of User Comments on Social Networks
• Author: Tomislav Marinković
• Mentor: Jan Šnajder (mentor)
• Committee member: Jan Šnajder (predsjednik povjerenstva)
• Committee member: Ante Đerek (član povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U zadnje vrijeme duboko učenje polako uzima maha i postavlja se kao način za izradu umjetne inteligencije. Jedan od važnih segmenta umjetne inteligencije je razumjevanje prirodnog jezika. U ovom radu dan je pregled nekih algoritama s kojim je moguće odrediti sentiment, emociju, temu i govorni čin iz komentara sa Facebook stranica hrvatskih telekomunikacijskih kompanija.

Abstract (english)

In recent years deep learning is starting to take off in the world of artificial intelligence, and is starting to be the default approach of machine learning. One of the most important parts of artificial intelligence is understanding natural language. In this thesis, some promising algorithms are looked into. Those algorithms can determine sentiment, emotion, topic, and speech act of users comments posted on Facebook.

• Keywords: Duboko učenje; obrada prirodnog jezika; analiza korisničkih komentara; neuronske mreže; sentiment; emocije; komentari; govorni čin
• Keywords (english): Deep learning; natural language processing; user comments analysis; neural network; word2vec; Facebook; sentiment; emotions; comments; speech acts
• Language: croatian
• URN:NBN: urn:nbn:hr:168:068873
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 22:40:51