Institutional Repository of Vilnius University
Mašininio mokymosi algoritmų taikymas neapykantos kalbos nustatymui iš lietuviško teksto /
Abstract
dc:descriptionIn this bachelor’s thesis, machine learning algorithms are used such as the support vector (SVM) classifier, the multi-layer perceptron (MLP) algorithm and the long short-term memory (LSTM) artificial neural network are used to solve hate speech detection problem for Lithuanian text. For training and testing, 1000 comments were selected from social media and news portals. First of all, data preprocessing was done, various vectorization techniques were tested for SVM, MLP classifiers, also hyperparameter tuning methods were applied in order to reach the highest accuracy for machine learning algorithms. After evaluating the accuracy of each of the mentioned methods, the most effective one was determined – LSTM.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Rasimavičiūtė, Raminta,
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:ELABAETD146240153&prefLang=en_US