基于相关向量机的网络舆情反转预测研究

  • 打印
  • 收藏
收藏成功


打开文本图片集

摘  要: 根据前人研究成果对网络舆情影响因素进行分析,构建出基于相关向量机的网络舆情反转预测模型。通过对46个舆情事件的训练和预测,发现相关向量机的预测精度和预测时间均优于支持向量机。由此可知,相关向量机具有良好的应用前景,对于及时发现反转舆情,规避舆情反转风险具有现实意义。

关键词: 网络舆情; 舆情反转; 相关向量机; 支持向量机

中图分类号:G206.3          文献标识码:A     文章编号:1006-8228(2023)05-113-05

Research on the prediction of network public opinion reversal

based on relevance vector machine

Ai Jingyi, Geng Liang, An Yu, Hu Zirui

(School of Science, Hubei University of Technology, Wuhan, Hubei 430068, China)

Abstract: In this paper, we analyze the influencing factors of network public opinion, and construct a prediction model of network public opinion reversal based on RVM. Through the training and prediction of 46 public opinion events, it is found that the prediction accuracy and prediction time of RVM are better than those of SVM. It can be seen that RVM has good application prospects, which is of practical significance for timely detection and avoidance of the risk of public opinion reversal.

Key words: network public opinion; public opinion reversal; relevance vector machine (RVM); support vector machine (SVM)

0 引言

据第49次《中国互联网络发展状况统计报告》显示,截至2021年12月,我国网民规模达10.32亿,网民人均每周上网时长为28.5小时[1]。(剩余5920字)

monitor
客服机器人