【摘要】 为了提高对社交网络舆情监测和管理能力,本文提出一种基于相空间重构的社交网络舆情智能化检测方法。在重构的相空间中提取社交网络舆情采样时间序列的统计平均值和信息熵;采用混沌非线性时间序列分析方法进行社交网络舆情采样序列的回归分析;对采集的社交网络舆情采用判决反馈均衡调节方法进行社交网络舆情统计特征量混频处理,提取社交网络舆情的统计信息特征量;采用支持向量机方法进行社交网络舆情的状态评估和标准性对比,在重构的相空间中实现社交网络舆情智能化检测。仿真结果表明,该方法进行社交网络舆情检测的准确性较高,智能性较好。更多还原

【Abstract】 In order to improve the ability of monitoring and managing public opinion in social networks, an intelligent detection method for public opinion in social networks based on phase space reconstruction is proposed. The phase space is reconstructed by using the non-linear processing method of social network public opinion sampling sequence. The statistical average and information entropy of social network public opinion sampling time series are extracted from the reconstructed phase space. The chaotic non-linear time series analysis method is used to carry out the regression analysis of social network public opinion sampling sequence, and the collected social network public opinion is analyzed. Feedback balanced adjustment method is used to mix the statistical features of social network public opinion, extract the statistical information features of social network public opinion, and support vector machine method is used to evaluate the status of social network public opinion and compare the standards. Intelligent detection of social network public opinion is realized in reconstructed phase space. The simulation results show that the method is accurate and intelligent in social network public opinion detection.更多还原