Stvaranje profila političara kroz analizu sadržaja objavljenog na društvenim mrežama

master's thesis

• Title (english): Generating politician profiles based on content analysis of social network datasets
• Author: Klara Grčić
• Mentor: Vedran Podobnik (mentor)
• Committee member: Vedran Podobnik (predsjednik povjerenstva)
• Committee member: Ignac Lovrek (član povjerenstva)
• Committee member: Marina Bagić Babac (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Korištenje društvene mreže Facebook u političkom kontekstu je postalo veoma važno u analizi podataka, kao i za praćenje mišljenja političara i javnosti. U sklopu ovog magistarskog rada radni okvir za analizu statusa s Facebooka je dizajniran i implementiran. Napravljena je kvantitativna i kvalitativna analiza tih statusa. Prikupljeni su statusi hrvatskih ministara i članova Europske komisije, koji su zatim pročitani i kategorizirani po sadržaju. Za svaku kategoriju svakog skupa podataka, uspoređen je broj statusa koji imaju oznaku sviđa mi se, podijeljenih statusa i komentara na statuse. Osim deskriptivne analize rezultata, napravljeni su i t-testovi kako bi se utvrdilo postoje li statistički značajne veze između promatranih varijabli. Rezultati su pokazali da su informativni statusi najčešći, dok su prošli događaji nešto o čemu političari najmanje pišu. S druge strane, statusi o prošlim događajima imaju najviše oznaka sviđa mi se, najviše su puta podijeljeni i komentirani.

Abstract (english)

The use of social network Facebook in political context has become very important in data analysis, as well as in observing politicians’ and public opinion. As part of this master thesis, framework for Facebook statuses analysis was designed and implemented, as well as qualitative and quantitative analysis of these statuses. Croatian ministers’ and European Commissioners’ set of statuses was collected. These statuses were read and categorized by its content. For each category of each dataset, the numbers of likes, shares and comments were compared. Besides descriptive analysis of results, the t-tests were made to determine if there are statistically significant connections between observed variables. Results have shown that informational statuses were the most common, while the past events are something politician wrote about least. On the other hand, statuses about past events were most liked, shared and commented.

• Keywords: političari; Europska Komisija; Hrvatska Vlada; društveni mediji; Facebook; statusi; kategorije
• Keywords (english): politicians; European Commission; Croatian Government; social media; Facebook; statuses; categories
• Language: english
• URN:NBN: urn:nbn:hr:168:417260
• 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: 2018-02-06 09:00:04