BERT-based new coronal pneumonia epidemic situation microblog sentiment analysis method, equipment and medium

A technology of sentiment analysis and epidemic situation, applied in the field of public opinion analysis, can solve the problems of hyperparameter adjustment, failure to consider the changes of the epidemic situation and the development of public opinion, and poor accuracy, so as to achieve the effect of improving accuracy

Pending Publication Date: 2021-06-01
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI +1
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] (1) For research on the direction of epidemic sentiment analysis, there is currently no complete set of methods covering data collection, preprocessing, sentiment analysis, and evaluation analysis;
[0013] (2) The existing technical solutions for epidemic sentiment analysis did not adjust the hyperparameters of the sentiment analysis model for the epidemic-relate

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • BERT-based new coronal pneumonia epidemic situation microblog sentiment analysis method, equipment and medium
  • BERT-based new coronal pneumonia epidemic situation microblog sentiment analysis method, equipment and medium
  • BERT-based new coronal pneumonia epidemic situation microblog sentiment analysis method, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Aiming at the deficiencies of the prior art, this embodiment provides a BERT-based sentiment analysis method for microblogs during the COVID-19 epidemic. As attached to the manual figure 1 As shown, the specific scheme is as follows:

[0056] S1. Obtain Weibo public opinion information and epidemic data related to the new crown pneumonia epidemic;

[0057] S2. Preprocessing the microblog public opinion information to obtain microblog public opinion data;

[0058] S3. Perform sentiment analysis on the microblog public opinion data through the language model, and obtain sentiment analysis results;

[0059] S4. Process the sentiment analysis results according to the microblog public opinion information and epidemic data to obtain epidemic correlation analysis.

[0060] Specifically, S1. Obtain Weibo public opinion information and epidemic data related to the COVID-19 epidemic. This embodiment adopts the mode of Python crawler to collect data. A framework for using th...

Embodiment 2

[0112] According to the method proposed in Example 1, this embodiment proposes a BERT-based microblog sentiment analysis system for the novel coronavirus pneumonia epidemic. The specific plan is as follows:

[0113] A BERT-based microblog sentiment analysis system for the new crown pneumonia epidemic, as shown in the attached Figure 12 As shown, it includes acquisition unit, processing unit and analysis unit. Acquisition unit: used to obtain microblog public opinion information and epidemic data related to public opinion; processing unit: used to preprocess microblog public opinion information and obtain microblog public opinion data; sentiment analysis unit: used to analyze microblog through language model Sentiment analysis of public opinion data to obtain sentiment analysis results; result analysis unit: used to process sentiment analysis results based on Weibo public opinion information and epidemic data to obtain correlation analysis of the new crown pneumonia epidemic....

Embodiment 3

[0119] Figure 15 It is a schematic structural diagram of a computer device provided by Embodiment 3 of the present invention. Figure 15 The computer device 12 shown is only an example, and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0120] Such as Figure 15 As shown, computer device 12 takes the form of a general-purpose computing device. Components of computer device 12 may include, but are not limited to: one or more processors or processing units 16 , system memory 28 , bus 18 connecting various system components including system memory 28 and processing unit 16 . Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by device computer 12 and include both volatile and nonvolatile media, removable and non-removable media. System memory 28 may include computer system readable media in the form of volatile memory....

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a BERT-based new coronal pneumonia epidemic situation microblog sentiment analysis method, equipment and a medium. The method comprises the following steps: acquiring microblog public opinion information and epidemic situation data related to a new coronal pneumonia epidemic situation; preprocessing the microblog public opinion information to obtain microblog public opinion data; performing sentiment analysis on the microblog public opinion data through a language model to obtain a sentiment analysis result; and processing the sentiment analysis result according to the microblog public opinion information and the epidemic situation data to obtain correlation analysis of the new coronal pneumonia epidemic situation. According to the method, a set of sentiment analysis model integrating data crawling, cleaning, storage, analysis and visualization is constructed, epidemic situation data and microblog public opinion data are integrated, model hyper-parameters are adjusted on a data set, the model accuracy is improved, finally, mainland epidemic situation development conditions are summarized and analyzed stage by stage, the correlation between the new coronal pneumonia epidemic outbreak situation and the public opinion emotion change is obtained, and the method has important significance on public opinion monitoring and obtaining in the epidemic period.

Description

technical field [0001] The present invention relates to the field of public opinion analysis, in particular, to a BERT-based microblog sentiment analysis method, equipment, and medium for the novel coronavirus pneumonia epidemic. Background technique [0002] As an acute respiratory infectious disease, novel coronavirus pneumonia has been widely concerned by the society at home and abroad since its outbreak, and it is also the focus of public opinion. The new crown pneumonia epidemic has the characteristics of a pandemic, and the extent and severity of the epidemic's spread are deeply worrying. Therefore, analyzing the overall situation of the domestic epidemic and the development of related public opinion will help people to have a clear and intuitive understanding of the current development stage of the epidemic and the corresponding public opinion response, and make decisions on this basis. [0003] The existing research on public opinion analysis of the epidemic mainly ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/9536G06F16/951G06F40/126G06F40/151G06F40/216G06F40/284G06F40/289G06Q50/00G16H50/80
CPCG06F16/9536G06F16/951G06F40/216G06F40/289G06F40/284G06F40/126G06F40/151G06Q50/01G16H50/80
Inventor 蒋泓毅刘薇肖焯姜青山谭忠陈会
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products