Sustav za automatizirano određivanje tipa osobnosti

undergraduate thesis

• Title (english): System for automatized personality type detection
• Author: Dora Horvat
• Mentor: Ivica Botički (mentor)
• Committee member: Ivica Botički (predsjednik povjerenstva)
• Committee member: Mirjana Domazet-Lošo (član povjerenstva)
• Committee member: Tomislav Jagušt (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom je radu primjenom nadziranog strojnog učenja razvijen sustav za predviđanje Myers-Briggs tipa osobnosti, jednog od danas najkorištenijih modela osobnosti, na temelju internetskih objava korisnika. Pri razvoju modela binarnih klasifikatora korišteni su algoritmi logističke regresije, slučajnih šuma i naivnog Bayesova klasifikatora te su se kroz određene mjere procjene uspoređivale performanse modela, kako bi se na kraju izabrao jedan algoritam čiji je model ugrađen u izrađeno grafičko sučelje za previđanje tipa osobnosti. Implementacija modela izrađena je u programskom jeziku Python korištenjem poznatih knjižnica za obradu teksta i strojno učenje općenito.

Abstract (english)

In this paper a system for predicting the Myers-Briggs personality type, one of the most used personality models today, based on supervised machine learning was developed. The developed prediction model is based on online users’ posts. Logistic regression, random noise and naive Bayesian classifier algorithms were used in the development of a binary classifier model. Performance of the model was compared via evaluation measures, and a specific algorithm was chosen, whose model was then implemented as a UI for predicting personality types. Python programming language and well-known libraries for word processing and machine learning were used as part of the machine learning process.

• Keywords: strojno učenje; klasifikacija; analiza teksta; Myers-Briggs Type Indicator
• Keywords (english): machine learning; classification; text analysis; Myers-Briggs Type Indicator
• Language: croatian
• URN:NBN: urn:nbn:hr:168:044322
• 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: 2023-01-14 20:34:54