Institutional Repository of Vilnius University
Iš anksto apmokytų modelių taikymas sentimentų analizės uždavinio sprendimui /
Abstract
dc:descriptionThe main objective of this thesis is to apply pre-trained models to the task of sentiment analysis. To achieve this goal, an analysis of existing pre-trained models and traditional classification algorithms was conducted, selecting the most common classification techniques. Data sets created for solving sentiment analysis tasks were examined, and two of them were used for the study. The selected pre-trained models were applied to the sentiment analysis task, and their accuracy was compared with traditional classification algorithms. Based on the experimental results, conclusions were formulated.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kiršytė, Miglė,
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:ELABAETD210647055&prefLang=en_US