Evaluation Model of Microblog Information Confidence Based on BP Neural Network

摘要

As the carrier of social media, microblog has become an important broadcasting tool for news. However, the characteristics of microblog platform causes that they cannot provide effective mechanisms to avoid the transmission of rumours or false information. Then we take the information around the main context as the features of microblog classification, integrated with the context to form a mixed feature for feature extraction based on classification. The BP-based network is established to evaluate the confidence of news by the mixed features. During the simulations, we adopt the real data in certain large websites to perform detailed analysis on the features and model proposed in this paper. The results show that the improved evaluation model has better performance to distinguish the authenticity of the news. The mixed features can provide better review of discrimination so our model can effectively solve the problems on confidence evaluation and rumour detection.