Development of a Model to Identify Fake News using Artificial Intelligence

Various attempts have been made to identify different types of misinformation because news-related misinformation proves to be a major societal concern. Particularly in social networks, blogs, and online publications. People primarily choose web-based resources for daily news content alongside general knowledge acquisition during the time of pervasive internet access. News spreads fast across diverse user groups within a short span of time across an extensive geographical area because social media platforms (SMP) including Instagram, YouTube, Twitter, Facebook, and internet browsers have become increasingly popular. Fake news creates biased or partial opinion which leads to extensive negative outcomes during its propagation and distribution. Contest results often become subject to these deceptive social media tactics which support particular candidates' political objectives. Spammers exploit attractive news headlines as a way to create income-producing clickbait advertisements. Data verification becomes necessary from time to time. News producers create content with a single goal which includes making readers fall for untrue or fraudulent information. The supporting content for news remains difficult to find because its transparency level is low. The process of identifying genuine news requires supplementary information aligned with social media usage or social engagement functions to be provided. I dedicate this paper to establish two distinct categories for online news articles with the aid of artificial intelligence research combined with linguistic analysis and machine learning techniques. This process enables users to verify the authenticity of presented news content by sharing validation responsibilities which results in either valid or invalid classification.