Classification Algorithm of Network Public Opinion Text Information Based on BP Neural Network

Classification Algorithm of Network Public Opinion Text Information Based on BP Neural Network

연구 분야: Artificial Intelligence

학회: 2023 International Conference on Networking, Informatics and Computing (ICNETIC)

With the rapid popularization and development of cloud computing, big data, Internet and other multimedia technologies, text classification has achieved remarkable application results in many fields. In the era of Internet big data, how to mine useful information from text data is one of the contents of natural language processing. Besides making great breakthroughs in image recognition, deep learning BP neural network can also be applied to the classification of online public opinion text information. Compared with other algorithms, BP neural network is more stable and anti-jamming, and it works well in text classification. This paper describes the BP neural network algorithm and its application status in detail, introduces the general process of text classification, and discusses the related technologies of online public opinion text classification. At the same time, the adaptive resonance theory is introduced into the traditional neural network algorithm to construct an adaptive BP neural network algorithm. Compared with other traditional algorithms such as Knn, SVM, K-means and other algorithms, the experimental results show that the algorithm can be applied to the classification of public opinion text information, and at the same time can improve the recall rate and accuracy of network public opinion information. The classification and modeling of related information provide useful solutions.