Automatic False News Detection Using Machine Learning
Aslan, Lara (2023)
2023
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2023090725454
https://urn.fi/URN:NBN:fi:amk-2023090725454
Tiivistelmä
False news refers to false or misleading information presented as real news. In recent years, we have seen a growing trend on false news, especially on the Internet. The goal for this thesis was to study automatic false news detection using machine learning and natural language processing techniques, and to determine which of the techniques works the most effectively.
This thesis first studies what exactly is false news, how it differs from other types of misleading information, and the results achieved by other researchers about the same topic. After building a foundation to understand false news, and the various ways of automatically detecting it, this the-sis provides its own experiments. These experiments were done on four different datasets, one that was made just for this thesis, and using 10 different machine learning methods.
The results for this thesis were good, and the results answered the original research questions set up in the beginning of this thesis. From the experiments, this thesis could determine that pas-sive-aggressive algorithms, support vector machines, and random forests are the most efficient methods to automatically detect false news. This thesis also concluded that more complex ex-periments, such as using multiple levels of identifying false news, or detecting computer-generated false news, require more complex machine learning models.
This thesis first studies what exactly is false news, how it differs from other types of misleading information, and the results achieved by other researchers about the same topic. After building a foundation to understand false news, and the various ways of automatically detecting it, this the-sis provides its own experiments. These experiments were done on four different datasets, one that was made just for this thesis, and using 10 different machine learning methods.
The results for this thesis were good, and the results answered the original research questions set up in the beginning of this thesis. From the experiments, this thesis could determine that pas-sive-aggressive algorithms, support vector machines, and random forests are the most efficient methods to automatically detect false news. This thesis also concluded that more complex ex-periments, such as using multiple levels of identifying false news, or detecting computer-generated false news, require more complex machine learning models.