DETECTING FAKE NEWS ON SOCIAL MEDIA USING DEEP LEARNING MODEL

Abstract

The incidence of fake news on social media platforms is a considerable risk to society in terms of civic responsibility and impact. This research nourishes profilers with a significant deficiency in the identification validity and the timeliness of phony news detection within the SNS environment where a flood of information is disclosed to the users. The key findings of this work are that the creation and presentation of a new dataset for fake news detection in social media settings are the main contributions of the work. This dataset recreates the nature and features of social media language and content through which deep learning models can be trained most appropriately. Our goal is to equip social media consumers with skills in analyzing the information they come across so that they can be more informed Facebook users. Through making tools that can help users distinguish fake or unreliable information in hand, social media was designed to fight fake news to create a new generation of smart users. It is of particular importance in the present era when social media is the primary information source for most people. The proposed approach is based on deep learning methodologies to extract and perform textual and contextual features analysis, which means that the presented solution is the real-time identification of fake news and can positively contribute to improving the quality and reliability of social networks.