New Media Detection Technology Based on Big Data Network Intelligent Algorithm

With the continuous development of new media information on the Internet, it has become a vital task to monitor the information spread in new media by using emerging artificial intelligence technologies, such as Big data and machine learning, in order to maintain network order. However, currently existing information feature detection models are mostly based on the characteristics of specific content itself. The challenges faced by this type of information feature detection model include high risk of overfitting, insufficient generalization ability, and failure to fully explore the deep correlation features inherent in media information. Based on this, this article first uses the BERT model to extract multi-level semantics from social media post text content, and then uses GNN technology to obtain the visual characteristics of the image. It can adopt the GCN algorithm for optimization to improve the performance of GNN, which is difficult to quickly converge when facing complex social network topologies. Finally, this paper constructs an illegal information detection model based on Big data network intelligent algorithm. Experiments show that, compared with the two baseline methods of SVM-TS (Support Vector Machine Model for Tabu Search) and EANN (Event Adverse Neural Networks), the illegal information intelligent detection model proposed in this paper shows higher accuracy in identifying false information, rumors, real events and unconfirmed events.