Public policy participation degree evaluation method and system based on LDA and vector space model

Abstract

The invention provides a public policy participation degree evaluation method and system based on LDA and a vector space model. The method comprises the steps of obtaining a target public policy document and target dynamic data; performing word segmentation processing on the target public policy document and the target dynamic data by adopting a TF-IDF algorithm to obtain a document feature word segmentation set and a data feature word segmentation set; respectively extracting semantic information implied in the target public policy document and the target dynamic data through an LDA model to obtain a document-data matrix; constructing a vector space model based on the document feature word segmentation set and the data feature word segmentation set, and calculating the similarity between the target public policy document and the target dynamic data to obtain a similarity matrix; and performing linear weighting processing on the document-data matrix and the similarity matrix. According to the method, the degree of participation of citizens in public policies can be effectively evaluated, meanwhile, the problems of data sparsity and semantic loss are solved, and the accuracy and effectiveness of evaluation are improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a public policy participation evaluation method and system based on LDA and a vector space model. Background technique [0002] Public policy evaluation refers to the comprehensive judgment and evaluation of the necessity, feasibility, cost-benefit and implementation effect of the policy made by the evaluation subject through scientific evaluation tools and evaluation methods according to certain standards and procedures. risk, improve the efficiency of policy implementation, timely adjust and improve the unreasonable or imperfect policy establishment and implementation process, and establish theoretical basis and experience comparison for the formulation of new policies. Technical support for evaluation work. The process of public policy evaluation is inseparable from the participation of citizens. Citizens' participation in the system and implementation of publ...

AI Technical Summary

Problems solved by technology

[0003] At present, using text clustering methods in traditional data mining to detect topics in web texts is still the mainstream, and many related market products have come out. However, traditional text clustering algorithms do not perform well in terms of data dimensionality reduction and semantic expression. Ideal, which affects the accuracy and validity of the evaluation results

Images