Strojno učenje u predviđanju zadovoljstva kvalitetom života u studentskoj populaciji

master's thesis

• Title (english): Machine learning in predicting quality of life satisfaction in the student population
• Author: Damir Puškarić
• Mentor: Sanja Seljan (mentor)
• Committee member: Ivan Dunđer (predsjednik povjerenstva)
• Committee member: Vjera Lopina (član povjerenstva)
• Committee member: Sanja Seljan (član povjerenstva)
• Granter: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences); Zagreb
• Defense date and country: 2024-09-20, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences; Information Systems and Information Science

Abstract

Cilj ovog rada bio je procjena zadovoljstva kvalitetom života u kontekstu strojnog učenja te izrada modela uz primjenu algoritama strojnog učenja. U teorijskom dijelu prikazan je opis pojma strojnog učenja te analiza pristupa i algoritama strojnog učenja. Također je pružen uvid u teme mentalnog zdravlja i kvalitete života.
U praktičnom dijelu provedeno je istraživanje kroz primjenu strojnog učenja za predviđanje zadovoljstva kvalitetom života u studentskoj populaciji. Točnije, korišten je regresijski model nasumične šume. Glavni cilj istraživanja je bio prepoznavanje ključnih faktora koji utječu na zadovoljstvo kvalitetom života studenata i procjena učinkovitosti strojnog učenja u pružanju dovoljno preciznih predviđanja koja bi mogla pomoći u informiranju i stvaranju adekvatnih strategija za poboljšanje zdravlja i kvalitete života studenata.
Za potrebe rada je izrađen i evaluiran regresijski model nasumične šume koji je demonstrirao relativno visoku razinu preciznosti u predviđanju.. Model je prepoznao nekoliko ključnih faktora koji utječu na kvalitetu života: kvaliteta sna, društveni život, fizička aktivnost te osobna sigurnost. Ovi podaci ukazuju na višeznačnu strukturu pojma kvalitete života, naročito u studentskoj populaciji. Time se naglašava važnost za poboljšanjem određenih aspekata njihovih života kako bi se poboljšalo opće zadovoljstvo kvalitetom života. Saznanja dobivena iz provedenog istraživanja dodatno naglašavaju mogućnosti koje donosi izrada modela strojnog učenja u stvaranju strategija koje mogu značajno poboljšati kvalitetu života studenata.

Abstract (english)

The aim of this paper was to assess satisfaction with the quality of life in the context of machine learning and to develop a model using machine learning algorithms. The theoretical section provides a description of the concept of machine learning and an analysis of machine learning approaches and algorithms. Additionally, it offers insight into topics related to mental health and quality of life.
In the practical section, research was conducted through the application of machine learning to predict satisfaction with quality of life in the student population. Specifically, a random forest regression model was used. The main goal of the research was to identify key factors influencing students' satisfaction with quality of life and to assess the effectiveness of machine learning in providing sufficiently accurate predictions that could help inform and create appropriate strategies to improve student health and quality of life.
For the purposes of this paper, a random forest regression model was developed and evaluated, demonstrating a relatively high level of accuracy in prediction. The model identified several key factors affecting the quality of life: sleep quality, social life, physical activity, and personal safety. These findings indicate the multifaceted nature of the concept of quality of life, especially within the student population, emphasizing the importance of improving certain aspects of their lives to enhance overall satisfaction with the quality of life. The insights gained from the research further highlight the potential of machine learning models in developing strategies that can significantly improve the quality of life for students.

• Keywords: nadzirano strojno učenje; algoritmi; nasumična šuma; podaci; predviđanje
• Keywords (english): supervised machine learning; algorithms; random forest; data; prediction
• Language: croatian
• URN:NBN: urn:nbn:hr:131:793549
• Study programme: Title: Information Sciences; specializations in: Archivistics Study, Library Science, Information Sciences (research), Information Sciences (teaching), Museology and heritage management, Informatology; Course: Information Sciences (research); Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra informacijskih znanosti (magistar/magistra informacijskih znanosti)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-09-22 17:17:45