Analiza teksta u digitalnim sadržajima

master's thesis

• Title (english): Text analysis in digital contents
• Author: Sunčica Kosović
• Mentor: Dragan Jevtić (mentor)
• Committee member: Dragan Jevtić (predsjednik povjerenstva)
• Committee member: Marin Vuković (član povjerenstva)
• Committee member: Miljenko Mikuc (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-22, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom radu prikazano je korištenje klasifikacije kao vrste nadziranog strojnog učenja u svrhu analize teksta u digitalnim sadržajima prikupljenim sa društvene mreže Twitter. Nakon dohvaćanja podataka, napravljena je ručna klasifikacija prikupljenih objava, koje su uz pomoć Python biblioteka pretvorene u oblik pogodan za izgradnju klasifikatora. Korišten je Naivni Bayes-ov klasifikator i SVM(engl. Support Vector Machine) algoritam. Model na osnovu kojeg se nove objave klasificiraju unutar unaprijed određenih klasa implementiran je unutar web aplikacije koja konačne rezultate ispisuje na web sučelju.

Abstract (english)

This paper presents the use of classification as a type of supervised machine learning for the purpose of text analysis in digital content collected from the social network Twitter. Next step after retrieving dana was manual classification of that same data which were afterwards converted into a form suitable for building classifiers with the help of Python libraries. The Naive Bayes classifier and the Support Vector Machine (SVM) algorithm were used. The model based on which new posts are classified within predefined classes is implemented within a web application that prints the final results on a web interface.

• Keywords: klasifikacija; strojno učenje; digitalni sadržaj; python; web aplikacija
• Keywords (english): classification; machine learning; digital content; python; web application
• Language: croatian
• URN:NBN: urn:nbn:hr:168:214627
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 10:11:07