Institutional Repository of Vilnius University
Melagingų naujienų aptikimas tekstiniuose duomenyse remiantis natūralios kalbos apdorojimu ir mašininiu mokymusi /
Abstract
dc:descriptionThe main objective of the thesis is to develop a machine learning model for fake news detection using various natural language processing techniques and apply said model in developing a tool to detect fake news in a web environment. Five tasks were identified for the thesis: 1. Analyse the existing literature ; 2. Select and describe an appropriate text dataset; 3. Analyse and process the data; 4. Train a binary classification model and evaluate its accuracy; 5. Develop a tool to detect fake news in a web environment. All the identified tasks have been completed. An accuracy of 99.2% has been achieved in fake news detection, using a long short-term memory model combined with a global vector word representation technique. Additionally, a browser extension capable of real-time identification of fake news was developed. Keywords: natural language processing, machine learning, fake news detection, fake news, browser extension.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Naus, Adomas,
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:ELABAETD192842876&prefLang=en_US