Naslov
Using Natural Language Processing for Fake News Detection

Autori
Cvitanović, Ivana

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, diplomski rad, diplomski

Fakultet
Fakultet elektrotehnike i računarstva

Mjesto
Zagreb

Datum
13.07

Godina
2021

Stranica
56

Mentor
Bagić Babac, Marina

Ključne riječi
Natural Language Processing, Fake News ; Self-Attention ; Deep Learning ; Transfer Learning

Sažetak
Nowadays, fake news is one of major concerns in our society, that is a form of news consisting of deliberate disinformation or hoaxes spread via traditional news media or online social media. Thus, this thesis aims to explore state-of-the- art methods for detecting fake news based on natural language processing. Advantages and limitations of current detection techniques are discussed. An example of fake news detector is designed and implemented using current datasets that are available for this purpose and analysing linguistic features to extract key patterns in fake news.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA