A system and method for analyzing public opinion

Abstract

The invention discloses an analysis method of public opinion, which comprises the following steps: preprocessing public opinion information; word segmentation; according to the result of word segmentation, the word index being created and the word frequency being counted. dividing the data to be processed into a training set and a test set; defining the network structure; training the network model to save the eigenvalues; combined with the network model and eigenvalues, determining whether the new public opinion information is positive or negative public opinion, to achieve public opinion information judgment. According to the characteristics of the LSTM model, when the information enters the control unit, the control unit will judge the information, leave the information conforming to the rule and forget the information not conforming to the rule, so as to solve the problem of long sequence dependence in the neural network.

Description

technical field [0001] The present invention specifically relates to a public opinion analysis system and method. Background technique [0002] Public opinion refers to the socio-political attitudes that the public generates and holds toward social managers around the occurrence, development, and changes of intermediary social events within a certain social space. It is the sum of the beliefs, attitudes, opinions and emotions expressed by a large number of people about various phenomena and problems in society. Internet public opinion is formed rapidly and has a huge impact on society. It not only requires the close attention of party and government cadres at all levels, but also requires great attention from all walks of life. [0003] With the rapid development of the Internet in the world, network media has been recognized as the "fourth media" after newspapers, radio and television, and the network has become one of the main carriers to reflect public opinion. The main...

AI Technical Summary

Problems solved by technology

[0006] In view of the above problems, the present invention proposes a public opinion analysis system and method. According to the characteristics of the LSTM model, when information enters the control unit, the control unit will judge the information, keep the information that conforms to the rules, and forget the information that does not conform to the rules. This is used to solve the long sequence dependency problem in neural networks

Images