DDCO model based false news detection research

Abstract

With the rapid development of the information age, while the popularity of social media brings great convenience, it also brings some negative effects, such as the spread of false news. At present, the identification of fake news is still based on the personal screening ability, therefore, the intelligent and information-based automatic detection algorithm has become one of the hot issues of current research. Based on the characteristics of DCAN and DEFEND models, this paper proposes an novel model DDCO, which uses multi-layer collaborative attention mechanism to extract the most relevant information from the three dimensions of sentence level, word level and sentence-comment level respectively. Finally, the model designed in this paper is tested on Weibo and Twitter data sets, and the results show that the DDCO has a higher accuracy than the existing models, which provides an important reference for false news detection.