Profiliranje autora na društvenim mrežama pomoću strojnog učenja

undergraduate thesis

• Title (english): Author Profiling on Social Networks Using Machine Learning
• Author: Lukrecija Puljić
• 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: 2017-07-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Porastom broja korisnika društvenih mreža raste i zanimanje za sadržaj koji generiraju korisnici društvenih mreža. U analiziranje korisnički generiranog sadržaja ubraja se i profiliranje autora teksta, odnosno odre divanje demografskh karakteristika, kao što je spol i dob, autora teksta. Ovaj rad bavio se odrešivanjem spola autora i znanstvenog područja kojem pripada fakultet koji pohađa autor metodama strojnog učenja. Rad se sastoji od cijelog procesa prikupljanja podataka s Facebooka i foruma i preobrade podataka. Potom slijedi razvoj modela odre divanja spola i znanstvenog područja kojem pripada fakultet koji pohađa autor teksta. Provedeno je i eksperimentalno vrednovanje modela i statistička analiza dobivenih podataka.

Abstract (english)

As social networks gain more and more users, interest for the content they’re creating is growing also. Analysis of user generated content includes profiling text’s authors, and determining demographic characteristics, such as gender and age of the authors. The focus of this thesis was determining author’s gender and the scientific area of the author’s faculty, using machine learning methods. It consists of the complete process of gathering data off of Facebook and forums and transforming this data. Then there’s the development of the model used to determine the gender of the text’s author and scientific area of the author’s faculty. Experimental model evaluation and statistical analysis of the results was also done.

• Keywords: obrada prirodnog jezika; profiliranje autora; društvene mreže; hrvatski jezik; strojno učenje
• Keywords (english): natural language processing; author profiling; social network; Croatian language; machine learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:276294
• 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: 2019-03-14 00:15:31