基于社交媒体数据的应急决策大群体群智知识挖掘及其价值测度方法研究

Large group masses wisdom knowledge mining and value measurement method research in emergency decision-making based on social media data

本文针对突发事件下的社交媒体数据体量庞大,但能够辅助应急决策的大群体群智知识分布无序且价值难以测度的问题,提出了一种应急决策大群体群智知识挖掘及其价值测度方法。首先,基于社交媒体博文数据,依据特定应急决策知识框架,采用TF-IDF(term frequency-inverse document trequency)法和改进后的词汇链算法构建了应急决策大群体群智知识挖掘方法;然后,提出了博文热度计算方法,在此基础上根据知识的语义重要性计算博文包含的群智知识总价值,并使用Shapley函数对群智知识价值进行分配;最后,以“新冠疫情”事件为案例对方法进行应用,并通过对比分析说明了方法的有效性和优越性。

In recent years,public safety emergencies are increasing in our country,which puts forward higher requirements for the efficiency,accuracy and risk of emergency decision-making.The traditional emergency decision-making is mainly in the form of small-scale expert group.Therefore,the knowledge level and structure of experts have a great impact on the quality of emergency decision-making.However,with the gradual evolution of group decision-making into large group decision-making,it is necessary to increase the participation of the public,and make full use of the large-group crowd intelligence knowledge derived from the public in order to assist emergency decision-making.After an emergency,the public will quickly express their views on social media,which results in a large amount of data containing a wealth of large group masses wisdom knowledge in emergency decision-making.However,this knowledge is distributed in unstructured data with disordered and uneven quality.Therefore,it is difficult to extract and fuse them.On the other hand,most of the existing knowledge value measurement methods are based on the perspective of economic value,which is not suitable for measuring the value of large group masses wisdom knowledge in emergency decision-making.Therefore,it is necessary to develop a scientific and comprehensive mining and value measurement method for large group masses wisdom knowledge in emergency decision-making.In view of these problems,from the perspective of the public,this paper systematically proposes a method of large group masses wisdom knowledge mining and its value measurement in emergency decision-making based on social media data,so as to provide assistance for emergency decision-making.The main contents of this paper are divided into the following three parts.The first part proposes a large group masses wisdom knowledge mining method in emergency decision-making based on social media data.Firstly,based on a previous study,the definition and framework of large group masses wisdom knowledge for emergency decision-making are proposed.In the second part,the blog posts under specific emergencies in social media are crawled and cleaned.