Sustainable intelligent outbreak with self-directed learning system and feature extraction approach in technology. (17th March 2023)

• Record Type: Journal Article
• Authors: Regin, R.; Rajest, S. Suman; Singh, Bhopendra; Obaid, Ahmed J.; Shynu, T.; Priscila, S. Silvia
• Is Part Of: International journal of intelligent engineering informatics. Volume 10:Number 6(2022)
• Page Start: 484
• Page End: 503
• Publication Date: 2023-03-17
• Subjects: transfer learning system -- machine learning -- convolutional neural network -- technology -- self-directed learning system -- COVID-19 -- false information -- postagging phrases; Artificial intelligence -- Engineering applications -- Periodicals; Engineering -- Computer programs -- Periodicals; Knowledge management -- Periodicals; 620.0028563
• Languages: English
• ISSNs: 1758-8715

Abstract

The COVID-19 epidemic is one of the deadliest viruses in recent history, but it is an infodemic that infects students and the community with false information, exacerbating the existing ailment. We attempt to identify and classify bogus news on the internet to identify false information about epidemics and coronavirus. Real comments were gathered from legitimate Twitter usernames, while phoney comments, publications, and events were obtained through realisation websites like news sources. Methods of deep learning, such as convolutional and recurrent neural networks, were combined in this process. Conventional classification techniques such as Binary Classification, K-nearest, Asymmetric Boost, and Random Forest were used up until they were exhausted in the random mutimodal deep learning (RMDL). Examining these tactics and gaining a deeper understanding of the dataset, including the information on COVID-19 that can be found on the internet, required the application of the high-frequency sub and clothing word convolutional extracted features.