Institutional Repository of Vilnius University
Kontekstinio rekomendavimo modelio sukūrimas /
Abstract
dc:descriptionIn this thesis context-aware recommender model is created and evaluated. In the first part of the paper, literature about recommender systems, their types, principles, advantages and drawbacks was analyzed. Context-aware recommender systems were described and concept of context and its incorporation in recommender systems is presented. In the next chapter context aware model is created and possible contexts for subject area are described. The experiments were conducted using 2017 Goodreads dataset. JODIE model was tested by modifying number of epochs and percentage of data used for model training, size of dataset and number of context features. During the work it was discovered that model has inconsistent increase of result accuracy, various means of improving recommendations were presented and positive impact of contextual data to recommendation accuracy was proven.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Černiavskytė, Irena,
- Contributors dc:contributor
-
- Būtėnas, Linas
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD107116388&prefLang=en_US