Identification of deception detection and fraudulent context on social media network applications

Abstract

newlineToday, the majority of individuals get their news through the newlineinternet. On social media, everyone may acquire and share information at any newlinetime and from anywhere. As a result, breaking news and rumors may spread newlinequickly on social media causing harm to society and the government. Various newlineprecautions must be taken in order to prevent the spread of this newlinemisinformation. Machine learning, deep neural networks, and other newlineapproaches are used in various rumor detection strategies. This research newlinefocuses on a comparison of several neural networks for rumor detection on newlinesocial media. A unique Reliable Deep Learning based Fake Account and Fake newlineNews Detection (RDL-FAFND) model for spotting counterfeit fake news and newlinefake accounts on social media was developed. The hyperparameters of the newlineDeep Sacked Auto Encoder (DSAE) model can be appropriately adjusted with newlinethe help of krill herding behavior. An ensemble learning technique raises the newlinesuccess rate for spotting fake news.