Profiliranje autora na društvenim mrežama

undergraduate thesis

• Title (english): Author Profiling of Social Media Users
• Author: Ivan Lovrenčić
• Mentor: Jan Šnajder (mentor)
• Committee member: Jan Šnajder (predsjednik povjerenstva)
• Committee member: Domagoj Alagić (član povjerenstva)
• Committee member: Zoran Medić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-09-17, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Profiliranje autora je metoda analize tekstova kod kojega se na temelju autorovog teksta otkrivaju odred̄ene informacije o autoru. Metode za profiliranje autora većinom se oslanjaju na stilometrijska obilježja teksta te su zbog toga izrazito korisne u današnjem svijetu obilježenom velikom brojem društvenih mreža. Ovaj rad se bavio odred̄ivanjem spola, dobi te intenziteta psihološki značajki autora. Modeli su se temeljili na alatima obrade prirodnog jezika i algoritmima strojnog učenja. Nakon... More razvoja modela za odred̄ivanje spola,dobi i intenziteta psiholoških značajki autora, provedeno je i eksperimentalno vrednovanje modela i analiza dobivenih podataka. Less

Abstract (english)

Author profiling is a method of analyzing a given number of texts to try to uncover
various characteristics of the author. Profiling methods are largely based on the stylometric features of the text and are therefore extremely useful in today’s world marked
by a large number of social networks. This paper deals with the determination of gen-
der, age, and intensity of psychological features of the author. The models were based
on natural language processing tools and machine learning... More algorithms. After the development of gender, age, and intensity of psychological features models, experimental
evaluation of the model and analysis of the obtained data was performed Less

• Keywords: obrada prirodnog jezika; profiliranje autora; društvene mreže; strojno učenje
• Keywords (english): natural language processing; author profiling; social networks; machine learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:803835
• 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: 2020-01-07 19:45:27