外部事件影响下的网络舆情失控风险分析仿真  

Simulation of Risk Analysis of Uncontrolled Network Public Opinion under Influence of External Events

在线阅读下载全文

作  者:伍永豪[1] 余正红[1] 周凤丽[1] 

机构地区:[1]武汉科技大学城市学院,湖北武汉430083

出  处:《计算机仿真》2015年第4期168-171,共4页Computer Simulation

基  金:中共省委高校工委;湖北省高等学校党建研究会2013-2014年度党建研究课题研究成果

摘  要:在对外部事件影响下的网络舆情失控风险进行报警的过程中,各个因素相互影响并且各因素独立存在,在外部因素影响下复杂性更高,无法进行准确分类并设定波动较小的权值,导致传统的网络舆情失控风险报警方法,在利用决策树分类算法对舆论数据进行分类时候,不能客观、准确的对失控风险进行量化计算,无法实现失控风险的有效报警。提出基于外部事件分析的网络舆情失控风险报警模型,确定可能引起网络舆情失控的外部事件,通过被报警网络舆情的实际情况,对失控风险后果的属性类型进行确定,给出失控风险后果属性与其权重,对每种外部事件引起失控的可能性以及可能产生的后果值进行分析,获取所有外部事件影响网络舆情失控的相对严重程度,对其进行排序,报警实现外部事件影响下网络舆情失控风险的准确报警。仿真结果表明,所提方法能够准确的实现失控风险报警,更适合应用于实际网络失控风险报警中。In the alarming process for the risk of uncontrolled network public opinion under the influence of external incidents, various factors affect each other but exist independently, and cannot be accurately classified, because the complexity is higher under the influence of external factors. A risk alarming model for uncontrolled network public opinion was put forward based on the analysis of the external event, so as to determine the external events which may cause uncontrolled network public opinion. By analyzing the actual conditions of network public opinion after being alarmed, the attribute types of the consequences of uncontrolled risk to were determined. According to the attributes and the weight, the possibility was analyzed for causing the out of control of each external incident and the conse- quence may occur. Relative severity of all external events effecting the uncontrolled network public opinion were ob- tained and sorted, so as to achieve the accurate alarming. The simulation results show that the proposed method can achieve accurate alarm for uncontrolled risk, and is more suitable for application in the alarm for actual network uncontrolled risk.

关 键 词:外部事件 网络舆情 失控风险 

分 类 号:TU22[建筑科学—建筑设计及理论]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象