情报科学

• • 上一篇    下一篇

基于信息关联的负面网络舆情风险分级与预测研究#br#

  

  1. 1. 河海大学统计与数据科学研究所,南京 210098

    2.上海对外经贸大学人工智能与变革管理研究院,上海 201620

Research on Risk Classification and Prediction of Negative Network Public Opinion Based on Information Correlation

  1. 1. Research Institution of Statistics and Data Science, Hohai University Nanjing 210098

    2. Research Institution of Artificial Intelligence and Innovation Management, Shanghai University of International Business and Economics, Shanghai 201620

摘要:

[目的/意义]网络社会充斥大量负面网络舆情,负面网络舆情风险分级和研判对提高网络治理能力和网络社会治理成效意义重大。[方法/过程]构建负面网络舆情风险指标体系,并采用熵权法计算风险指标权重;基于加权GRA模型计算灰色加权信息关联度,在此基础上,运用k-means聚类算法构建负面网络舆情风险分级方案,据此对负面网络舆情进行风险预测。[结果/结论]实证分析结果表明,所建负面网络舆情风险分级模型客观性强、可靠度高,可为负面网络舆情风险精准响应提供有效决策依据。

关键词:

负面网络舆情, 风险分级, 加权GRA, k-means聚类

Abstract:

 [purpose/significance]The network society is full of a large number of negative network public opinion. The risk classification and judgment of negative network public opinion is of great significance to improve the ability of network governance and the effectiveness of network social governance. [method/process] The risk index system of negative network public opinion is constructed, and the entropy weight method is used to calculate the weight of risk index; the grey weighted information correlation degree is calculated based on the weighted GRA model, and on this basis, the k-means clustering algorithm is used to construct the risk classification scheme of negative network public opinion, and then the risk prediction of negative network public opinion is carried out. [result/conclusion] The results of empirical analysis show that the model has strong objectivity and high reliability, which can provide effective decision-making basis for accurate response of negative network public opinion risk.

Key words:

negative network public opinion, risk classification, weighted GRA, k-means clustering