Sustav za preporučivanje korisničkih kompetencija na osnovi korisničkog unosa

undergraduate thesis

• Title (english): Hard Skill Autocompletion Recommender System
• Author: Nikolina Jukić
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Adrian Satja Kurdija (član povjerenstva)
• Committee member: Petar Afrić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Prelaskom u informacijsko doba započela je nagla digitalizacija. Povećanjem broja
korisnika interneta, broj dostupnih informacija neprestano raste i dolazi do preopterećenja informacijama. Rješavanje tog problema zahtijeva analizu i obradu podataka za što se, između ostalog, grade sustavi za preporučivanje. U radu je predloženo programsko ostvarenje sustava koji korisniku preporučuje kompetencije na osnovi poznatih informacija o njemu. Rad programskog rješenja i teorijska znanja potrebna za razvoj sustava detaljno su objašnjeni. Sustav je zasnovan na suradnji i preporuke stvara tražeći slične korisnike. Učinkovitost sustava ispitana je prikladno odabranim mjerama te su predstavljeni rezultati i mogućnosti poboljšanja trenutnog rješenja.

Abstract (english)

Advancement to the information age led to rapid digitalization. Increase in the
number of Internet users and available digital information leads to information overload. Solving this problem requires work in information analysis and processing, for
that purpose recommender systems are built. This paper proposes a realization of a
system used to recommend skills to the user, based on previously accumulated information about the user. The paper presents functionality of the system, as well as theory
knowledge needed for building such a system. Built system is a collaborative recommender system that gives recommendations based on similarities between users. Work
of the system is tested using appropriate evaluation measures. Finally, the results of
the evaluation and possible improvements of the current system are discussed.

• Keywords: Jaccardova sličnost; Python; sustav zasnovan na suradnji; mjere sličnosti; vrednovanje sustava
• Keywords (english): Jaccard similarity; Python; collaborative recommender system; similarity measures; system evaluation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:019648
• 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 20:42:48