Public opinion propagation prediction method and system based on social network public opinion dynamic model

• Main Authors: LIAO WEI, LIU WANGYANG, CAO LIRU, SHEN YI, ZHOU YONGLIN, ZHANG LICAN, JIA YU
• Format: Patent
• Language: Chinese; English
• Published: 23.02.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention belongs to the technical field of network information processing, and discloses a public opinion propagation prediction method and system based on a social network public opinion dynamic model. According to the method, data preprocessing is completed by collecting topic propagation data in a real social network; constructing a Markov chain propagation model; then, taking different node influence vectors and the propagation degrees of topics at different moments as input, and training to obtain a Markov transfer matrix function expression of a Markov chain model; and finally, carrying out model performance test on the sub-network of the real social network. According to the method, the problem that the current public opinion propagation dynamic model does not consider different influences of nodes in the social network is solved, and the propagation process of public opinions in the social network is simulated more truly. 本发明属于网络信息处理技术领域，公开了基于社交网络舆论动力学模型的舆论传播预测方法及系统。该方法通过采集真实社交网络中的话题传播数据，完成数据预处理；