Modeli za predviđanje tipova ličnosti iz tekstova mrežnih rasprava na hrvatskome jeziku

master's thesis

• Title (english): Text-Based Personality Type Prediction from Online Discussion Texts in Croatian Language
• Author: Bartol Freškura
• Mentor: Jan Šnajder (mentor)
• Committee member: Jan Šnajder (predsjednik povjerenstva)
• Committee member: Marko Čupić (član povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Automatsko previd̄anje tipova ličnosti, odnosno najistaknutijih karakteristika ne-
kog pojedinca, na temelju tekstova autora sve je popularnije područje obrade prirodnog jezika s brojnim primjenama, od kliničke psihologije, savjetovanja i upravljanja
ljudskim resursima. Posebno široku primjenu imaju postupci za predvid̄anje tipova
iz tekstova na društvenim mrežama, primjerice u ciljanom oglašavanju, istraživanjima
tržišta i političkim istraživanjima. Postupci temeljeni na strojnom učenju i stilometrijskoj analizi pokazali su se razmjerno uspješnima u ovome zadatku.

Abstract (english)

Automatic personality type prediction based on the text of the authors is gaining
popularity in the field of natural language processing with many applications such as
in clinical psychology, counselling, and human resources management. Personality
prediction techniques have a particularly wide usage when applied on social networks,
e.g. targeted advertising, market research, and political targeting. Algorithms based on
the machine learning and stylometric analysis have shown great success at this task.

• Keywords: Tip ličnosti; Myers-Briggs; analiza; strojno učenje; Forum.hr; psihologija
• Keywords (english): Personality type; Myers-Briggs; analysis; machine learning; Forum.hr; psychology
• Language: croatian
• URN:NBN: urn:nbn:hr:168:809990
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 20:18:06