A Study On Topics Of Public Service Demand Based On The Co-word Cluster

In recent years,with the continuous development and improvement of China's economic level,the domestic economic system and social structure have begun to seek transformation and upgrading,the new social problems and a lot of interest demands are also increasing.Although all levels of governments have planned the goal of reform of the supply side of basic public services,increased financial input,and generally established a basic public service system,they face the contradiction between the rapid growth of basic public service demand and the lack of effective supply and imbalance.With the emergence of various smart cities and smart government projects,the political and civil interaction approaches have been further expanded,and the public appeals have been changed from passive to active.Big data texts have become an important carrier for the expression of public public service demand.In this context,the grasp of the topics of public service demand has become possible,which has brought opportunities for the government to optimize public service resources and improve public service satisfaction.In the past,scholars used social survey methods to study the topics of public service demand.Due to the size,objectivity and workload of data,it is difficult to become a normalization tool and cannot meet the needs of the big data era.In order to adapt to the requirements of the new era,this paper intends to introduce the Co-word Analysis into the research of the topics of public service demand,and proposes a topic mining method of public service demand based on the Co-word Analysis,and studies the applicability and usefulness of this method in the study of public service demand.Firstly,by studying the application results of the Co-word Analysis,the general pattern of the application of the Co-word Analysis is summarized,that is,the Co-word Topics Mining Model.Based on the model,a topic mining method of public service demand based on the Co-word Analysis is proposed,and the objective conditions and process of the method are explained.Secondly,the method of drawing the strategic coordinate graph in the Co-word Analysis is improved.A method based on Pagerank and graph theory is proposed.And numerical experiments show that the improved strategic coordinates are more discrete and the application effect is better.Thirdly,A Kmedoide co-word clustering method based on CFSFDP algorithm is proposed.Through the numerical experiments of public service appeals,it is proved that this method has better clustering performance than other co-word clustering methods,and is more suitable for the research of public service demand topics mining;Fourthly,the improved Co-word Analysis proposed in this paper is integrated into the research of public service demand topics mining.Taking Fuzhou City as an example,the topic mining method of public service demand based on the Co-word Analysis is comprehensively explained to verify the feasibility and effectiveness of the method.Fifthly,the topics of public service demand in Fujian Province was explored and analyzed.The results show that although there are differences in the composition and characteristics of demand topics in different cities,transportation,real estate market supervision,and civilized city construction are all at a relatively core position,indicating that these three public service demands play an important role in the Fujian public service network.On the basis of the status quo,suggestions and countermeasures for the improvement of public service capacity and the allocation of public service resources in Fujian Province are proposed.Finally,the thesis is summarized.On the one hand,the research proves that the improved strategy of the Co-word Analysis proposed in this paper is effective and feasible.On the other hand,the feasibility of the Co-word Analysis in the study of public service demand is tested by the study of the topics of public service demand in Fujian Province,and provides operational countermeasures and suggestions for the effective allocation of public service resources in Fujian Province.