| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Izdelava interaktivnega priporočilnega sistema za predlaganje člankov in knjig s pomočjo strojnega učenja : magistrsko delo
Authors:ID Polner, Mitja (Author)
ID Žlahtič, Bojan (Mentor) More about this mentor... New window
Files:.pdf MAG_Polner_Mitja_2026.pdf (2,15 MB)
MD5: 594BBAF57D7B4E63D88332DE3F21777A
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V magistrskem delu smo zgradili semantični priporočilni sistem, ki je glede na uporabnikove zahteve priporočal članke in knjige na tri različne načine. Ti načini so: priporočanje glede na podani naslov ali kontekst in priporočanje po ostalih podobnih člankih ali knjigah. Za priporočanje smo uporabili modele TF-IDF, word2vec, BERT in GPT ter veliki jezikovni model za generiranje odgovorov. Semantično podobnost med dokumenti in vhodom uporabnika smo izračunali s pomočjo kosinusne podobnosti. S testiranjem modelov z različnimi metrikami smo ugotovili, da se v vseh primerih priporočanja najboljše izkaže model BERT.
Keywords:obdelava naravnega jezika, veliki jezikovni modeli, generiranje z razširjenim iskanjem, priporočilni sistem
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[M. Polner]
Year of publishing:2026
Number of pages:1 spletni vir (1 datoteka PDF (XII, 73 str.))
PID:20.500.12556/DKUM-97764 New window
UDC:004.85:004.774.2(043.2)
COBISS.SI-ID:281714435 New window
Publication date in DKUM:29.05.2026
Views:187
Downloads:14
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:10.04.2026

Secondary language

Language:English
Title:Development of an interactive recommendation system for suggesting articles and books using machine learning
Abstract:The master's thesis aimed to create a semantic recommendation system for books and articles using 3 different methods based on the user's input. These methods are: recommending based on titles, based on context and based on other similar articles and books. We used TF-IDF, word2vec, BERT and GPT models for recommendations and a large language model for generating a response. We calculated the semantic similarity between documents and user input using cosine similarity. From our testing of models with different evaluation metrics we found that the BERT model performed better in all recommendation cases.
Keywords:natural language processing, large language model, retrieval-augmented generation, recommendation system


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica