Amadori, Marco (A.A. 2022/2023) Fake news spread and detection: a network and machine learning approach. Tesi di Laurea in Data science in action, Luiss Guido Carli, relatore Giuseppe Francesco Italiano, pp. 76. [Master's Degree Thesis]

Preview

PDF (Full text) Download (9MB) | Preview

Abstract/Index

Context setting. Research questions. Literature review. Approaches to confront fake news. Introduction to fake news and its detection. Why does fake news matter? How is fake news spread? Social network theory basics. Measures of networks. A case study: Russian interference in 2016 US elections. Fake news detection: a machine learning approach. Proposed framework. Data collection and preparation. Preprocess data. Feature extraction. Algorithms. Training and validation. Model evaluation-performance metrics. Continuous improvement. Transparency. User accessibility. Classification of fake and non-fake news using machine learning. Data inspection and initial steps. Model selection and training. Theoretical implementation of BERT in fake news detection. Theoretical background of BERT. Detailed explanation of BERT’s model in fake news detection. ARGUS: development of an interactive front-end for fake news classification. Technologies. Development process.

References

Bibliografia: pp. 72-73.

Thesis Type:	Master's Degree Thesis
Institution:	Luiss Guido Carli
Degree Program:	Master's Degree Programs > Master's Degree Program in Data Science e Management (LM-91)
Outstanding Thesis:	Department of Business and Management
Chair:	Data science in action
Thesis Supervisor:	Italiano, Giuseppe Francesco
Thesis Co-Supervisor:	Sinaimeri, Blerina
Academic Year:	2022/2023
Session:	Extraordinary
Deposited by:	Alessandro Perfetti
Date Deposited:	08 Jul 2024 13:06
Last Modified:	25 Jul 2024 15:21
URI:	https://tesi.luiss.it/id/eprint/39196

Downloads

Repository Staff Only

View Item