Alati generativne umjetne inteligencije u obrazovanju

master's thesis

• Title (english): Generative artificial intelligence tools in education
• Author: Patricija Petanjek
• 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: 2024-09-13, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences; Organization and Informatics

Abstract

Brzi napredak umjetne inteligencije, posebno u obradi prirodnog jezika i razvoju naprednih jezičnih modela, značajno je utjecao na obrazovanje. Ovaj rad istražuje transformativni potencijal generativne umjetne inteligencije u obrazovnim okruženjima, ističući njezine koristi poput unapređenja nastavnih metodologija, personaliziranog učenja i pojednostavljenja administrativnih procesa. Također se razmatra kako ovi alati mogu podržati akademsko istraživanje kroz automatizaciju zadataka poput pregleda literature i parafraziranja. U okviru rada provedeno je istraživanje s ciljem ispitivanja potencijala GPT modela za optimizaciju studentskih upita na hrvatskom jeziku. Istraživanje se fokusiralo na dva ključna pitanja: može li se GPT model prilagoditi specifičnim obrazovnim zadacima i može li se automatizirati proces prompt inženjeringa u obrazovanju. Evaluacija rezultata pokazala je da GPT modeli mogu značajno poboljšati preciznost i relevantnost odgovora, čime se unapređuje kvaliteta interakcije između studenata i AI alata. Ovaj rad doprinosi dubljem razumijevanju uloge generativne umjetne inteligencije u obrazovanju te nudi strateške smjernice za njezinu etičku i učinkovitu implementaciju. Kroz kombinaciju teorijske analize i praktičnih istraživanja, pružaju se vrijedni uvidi koji mogu informirati buduće razvojne pravce i podržati inovacije usmjerene prema personaliziranijim i pristupačnijim obrazovnim iskustvima.

Abstract (english)

The rapid advancement of artificial intelligence, particularly in natural language processing and the development of advanced language models, has significantly impacted education. This paper explores the transformative potential of generative artificial intelligence in educational settings, highlighting its benefits such as enhancing teaching methodologies, personalized learning, and simplifying administrative processes. It also examines how these tools can support academic research by automating tasks such as literature reviews and paraphrasing. The study conducted within this paper aims to assess the potential of GPT models for optimizing student prompts in the Croatian language. The research focused on two key questions: whether a GPT model can be adapted to specific educational tasks and whether the process of prompt engineering in education can be automated. The evaluation of the results showed that GPT models can significantly improve the accuracy and relevance of responses, thereby enhancing the quality of interaction between students and AI tools. This paper contributes to a deeper understanding of the role of generative artificial intelligence in education and offers strategic guidelines for its ethical and effective implementation. By combining theoretical analysis and practical research, valuable insights are provided that can inform future development paths and support innovations aimed at more personalized and accessible educational experiences.

• Keywords: Umjetna inteligencija; generativna umjetna inteligencija; obrazovanje; istraživanje; akademsko pisanje; etičnost; alati umjetne inteligencije
• Keywords (english): Artificial intelligence; generative artificial intelligence; education; research; academic writing; ethics; artificial intelligence tools
• Language: croatian
• URN:NBN: urn:nbn:hr:131:441114
• 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: 2024-09-16 09:54:22