Public psychological assessment method in an emergency

Abstract

The invention relates to a public psychological assessment method under an emergency, which is a Batch SVM increment psychological assessment algorithm based on a Boosting algorithm, and the algorithmmainly generates a series of weak classifiers through operation on a sample set, and updates a support vector machine classifier by replacing partial training samples through iteration. And then weighted integration is carried out on the weak classifiers to generate a final fusion strong classifier. With the adoption of the method, a more accurate public psychological assessment result can be obtained; Meanwhile, an online psychological assessment mechanism is constructed, so that public psychological conditions in network emergencies can be analyzed online in real time, and the method can beapplied to a large distributed psychological assessment system based on a cloud platform, is simple to implement and high in accuracy, greatly reduces psychological assessment time delay, and has very high application value and practical significance.

Description

technical field [0001] The invention belongs to the technical field of big data analysis and application, relates to public opinion analysis, and in particular to a public psychological evaluation method under emergencies. Background technique [0002] With the advent of the era of big data, the Internet has developed rapidly, and netizens can actively participate in social management through the Internet. At the same time, network emergencies are occurring more and more frequently, and their influence has entered real life from cyberspace, and from virtual issues to social reality. The government is facing new challenges in managing emergencies and crises. It has become an unavoidable important task for our government to attach great importance to network emergencies, especially to evaluate the public's psychology in order to effectively strengthen their coping capabilities. [0003] In the prior art, public psychological assessment methods for emergencies are divided into...

AI Technical Summary

Problems solved by technology

Among the methods based on machine learning, the existing machine learning methods face the problem that the training model takes a long time, and this problem is more prominent when the amount of data is huge

And the model cannot be updated with the increase of data, and cannot meet the dynamics of real-time update of the model

In the method based on deep school, the traditional psychological assessment method takes a long time to train the model, and it is impossible to analyze the public psychology in time during the emergency

Images