Machine Learning Base Algorithms Using Truncated Singular Value Decomposition as a Novel Solution for Fake News Analysis and Detection

Hashim Ibrahim Bisallah & Umoru Yahaya Ibrahim

Machine Learning Base Algorithms Using Truncated Singular Value Decomposition as a Novel Solution for Fake News Analysis and Detection

Abstract: Fake news analysis and detection is a method that requires using machine learning classifiers to recognize and detect news content as fake or real. No research work has been carried out on fake news analysis and detection using the machine learning algorithms using Truncated singular value decomposition (TSVD) on the ‘ISOT Fake News Dataset’ but there is a need for a better design that can provide better accuracy. This research aims to develop and use systematic progression in identifying fake news analysis using machine learning algorithms with TSVD. The machine learning algorithms which include the light Gradient Boosting Machine, Cat boosting classifier, and support vector machine with TSVD were used on ‘The ISOT Fake News Dataset’ to recognize the fake news from real news in the dataset, thereby improving the performance of these classifiers by cleaning the data to manage the data imbalances more efficiently. The recommended design yields an exactness of 97.33%. The postulated technique out classifies the current classifiers which possess an exactness of 95.05%. We recommend that Machine learning classifiers using TSVD should be applied in Fake News analysis and detection since it gives a better performance accuracy in fake news analysis and detection

KJSET Volume. 3, Issue 1 (2024)

Contributor(s)

Keywords

Download Full-text (PDF)

Machine Learning Base Algorithms Using Truncated Singular Value Decomposition as a Novel Solution for Fake News Analysis and Detection