Implementacija algoritma za klasifikaciju lažnih vijesti utemeljen na javno dostupnim bazama podataka lažnih vijesti

master's thesis

• Title (english): Fake News Classification Based on Publicly Available Fake News Datasets
• Author: Dora Šegvić
• Mentor: Dario Bojanjac (mentor)
• Committee member: Dario Bojanjac (predsjednik povjerenstva)
• Committee member: Marko Bosiljevac (član povjerenstva)
• Committee member: Jelena Božek (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Zbog naglog porasta pojave lažnih vijesti (engl. fake news) na web portalima i društvenim mrežama pojavila se potreba za razvojem računalnog algoritma koji će biti u stanju provjeriti istinitost vijesti. Razvoj takvog algoritma temelji se na skupovima podataka, odnosno javno dostupnim bazama lažnih vijesti. U radu su opisane različite dostupne baze koje se mogu koristiti, te je prikazana i opisana implementacija jednog modela koji uspješno klasificira vijesti u dvije kategorije – istina i laž.

Abstract (english)

Due to large increase of fake news on news portals and social networks there is a need to develop a computer algorithm that will be able to verify whether the news article is true or not. Development of such algorithm is based on publicly available fake news databases. This paper lists a few available databases that can be used. In addition, it presents and describes the implementation of a model that successfully classifies news articles into two categories – true and fake.

• Keywords: lažne vijesti; baze vijesti; strojno učenje; logistička regresija; TF – IDF vektorizacija
• Keywords (english): fake news; fake news databases; machine learning; logistic regression; TF – IDF vectorization
• Language: croatian
• URN:NBN: urn:nbn:hr:168:454296
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 10:00:56