Sustav preporuka za znanstvenu literaturu

master's thesis

• Title (english): Recommendation system for scientific literature
• Author: Borna Artić
• Mentor: Boris Vrdoljak (mentor)
• Committee member: Boris Vrdoljak (predsjednik povjerenstva)
• Committee member: Vedran Mornar (član povjerenstva)
• Committee member: Marko Horvat (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-03, Croatia

Abstract

U ovom diplomskom radu demonstrirana je primjena sustava preporuka kao rješenja problema informacijske prezasićenosti na internetu. Preporučitelj koji je implementiran s ciljem primjene u domeni znanstvene literature koristi tehnike suradničkog filtriranja i filtriranja temeljenog na sadržaju. Podaci o istraživačkim radovima nad kojima se algoritmi primjenjuju dohvaćeni su s javno dostupne platforme za distribuciju znanstvenih članaka arXiv. Izrađena je i web aplikacija koristeći sustav za upravljanje relacijskim bazama podataka MySQL i radne okvire React i Rails koja korisnicima pruža mogućnost interakcije sa sustavom preporuka: na temelju aktivnosti unutar aplikacije i postojećih preferencija generiraju se nove, personalizirane preporuke.

Abstract (english)

This thesis showcases the utilization of a recommendation system as a solution to the issue of information overload on the Internet. The implemented recommendation system focuses on the domain of scientific literature and incorporates collaborative filtering and content-based filtering techniques. The data on the research papers utilized for algorithms application were acquired from arXiv, a free distribution service and an open-access scholarly articles archive. To enhance user engagement with the recommendation system, a web application was developed using the MySQL relational database management system along with the React and Rails frameworks. This application generates new and personalized recommendations based on the user's activities within the application and existing preferences.

• Keywords: sustav preporuka; filtriranje temeljeno na sadržaju; suradničko filtriranje; web aplikacija; baza podataka
• Keywords (english): recommendation system; content-based filtering; collaborative filtering; web application; database
• Language: croatian
• URN:NBN: urn:nbn:hr:168:201909
• 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: 2023-07-13 09:53:02