Semantička analiza korisničkih interakcija u telekomunikacijskoj industriji

master's thesis

• Title (english): Semantic analysis of user interactions in the telecommunications industry
• Author: Andrea Pirša
• Mentor: Željka Car (mentor)
• Committee member: Željka Car (predsjednik povjerenstva)
• Committee member: Vedran Podobnik (član povjerenstva)
• Committee member: Marina Bagić Babac (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U telekomunikacijskoj industriji prepoznat je utjecaj kvalitete korisničkih interakcija na uspješnost poslovanja. Obrada nestrukturiranih podataka generiranih digitalnim ili tradicionalnim načinima interakcije iziskuje upotrebu programskih rješenja uglavnom zasnovanih na postupcima semantičke analize. U radu su opisani pristupi i tehnologije korišteni u dosadašnjim istraživanjima semantičke analize. Uz implementacijske tehnologije i arhitekturu razvijenog rješenja za semantičku analizu u telekomunikacijskoj domeni, objašnjen je primijenjeni pristup temeljen na kombinaciji algoritma Naive Bayes i jezičnih pravila. Osnovni cilj rada je razviti prijedlog modela za semantičku analizu interakcija u svrhu poboljšanja poslovanja operatora.

Abstract (english)

The effect of user interactions on the business success is recognized by the telecommunications industry. Unstructured data generated by digital and traditional interaction channels is processed by software solutions which are generally based on semantic analysis. In this theses approaches and technologies used in previous semantic analysis researches are described. In addition to implementation technologies and architecture of the developed software solution for semantic analysis in the telecommunications domain, this thesis also presents the applied approach based on the combination of Naive Bayes algorithm and language rules. The aim of this thesis is to develop a proposal of model for semantic analysis of interactions to improve business achievements of the telecommunications operators.

• Keywords: telekomunikacijska industrija; korisničke interakcije; semantička analiza; sentiment; Naive Bayes algoritam
• Keywords (english): telecommunications industry; user interactions; semantic analysis; sentiment; Naive Bayes algorithm
• Language: croatian
• URN:NBN: urn:nbn:hr:168:770212
• 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: 2019-03-14 00:00:29