基于贝叶斯网络的网络舆情案例匹配模型

A Model of Case Matching for Internet Public Sentiment Based on Belief Network

[目的]通过研究当下网络环境的具体情境,利用概率分析的方式判断具体舆情所属的案例类型,从而为网络舆情危机响应决策提供依据。[方法]使用贝叶斯网络模型作为分析方法,构建网络舆情案例匹配的指标体系和案例匹配模型。[结果]通过48个网络舆情危机中的随机43个事件作为训练数据,构建贝叶斯网络模型,使用剩余5个网络舆情危机事件作为测试组,经检验测试样本案例匹配结果与事实相符。[结论]本文通过构建网络舆情案例匹配的相关指标体系和贝叶斯网络模型,为对网络舆情进行分型,从而为舆情危机响应提供了决策依据。

[Purpose/Significance]According to the concurrent Internet circumstance,the paper proposed a method to classify certain internet public sentiment instance based on probability analysis.Therefore it provided knowledge which was need for decision making in Internet public sentiment crisis-response.[Method/Process]Using belief network,it constructed the Internet public sentiment index system and Internet public sentiment case matching model.[Result/Conclusion]Using 43 out of 48 Internet public sentiment crises as training data,trained the belief network.The remaining 5 crises were then used as test set.All 5 crises were labeled correct according to the belief network.[Conclusion]The Internet public sentiment index system and belief network could classify Internet public sentiment crisis correctly,therefore providing solid basis for decision making in public sentiment crisis-response.