Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Microblog sentiment classification method based on sentiment category description

A classification method and category technology, applied in text database clustering/classification, neural learning method, text database query, etc., can solve the problem of not considering emotional category semantic information

Active Publication Date: 2022-05-17
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The invention provides a microblog emotion classification method based on emotion category description to solve the problem that the traditional method does not consider the semantic information of emotion category in the task of microblog emotion classification

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
  • Microblog sentiment classification method based on sentiment category description
  • Microblog sentiment classification method based on sentiment category description
  • Microblog sentiment classification method based on sentiment category description

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] Embodiment 1: as figure 1 As shown, based on the microblog emotion classification method described by the emotion category, the specific steps of the method are as follows:

[0019] Step1. Microblog data is collected from the Sina Weibo platform, and 8306 microblogs are retained as the experimental data set. And carry out preprocessing operation, the manual label of each Weibo is: one of the five categories of happiness, anger, sadness, fear and neutral. Then, according to the ratio of approximately 8:1:1, the experimental data set is divided into training set, verification set and test set. The specific data set distribution is shown in Table 1;

[0020] Table 1 Division of experimental data sets (unit: bar)

[0021]

[0022] In said Step1, the data preprocessing is implemented by writing a program in python language, and the text is deduplicated and the operations of characters such as " / / ", "@" and URL are deleted;

[0023] The design in this step is an importa...

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 relates to a microblog emotion classification method based on emotion category description, and belongs to the technical field of natural language processing. The present invention first proposes an emotion category description strategy, which expands all the emotion categories of microblogs to be classified into formalized category descriptions; secondly, splices the microblog text and category description into a question-answer pair, and inputs it into the pre-trained BERT model ;Secondly, input the hidden state of the question-answer pair encoded by the BERT model into the two-layer fully connected neural network, and output the fused semantic representation of the entire question-answer pair; finally, input the fused semantic representation of the question-answer pair into the Softmax layer, and output The normalized emotion category probability distribution realizes the emotion classification of Weibo. Compared with the baseline method BERT, the macro-average and micro-average F1 values ​​of the present invention are increased by 1.77% and 1.71%, respectively, which proves the effectiveness of the method of the present invention.

Description

technical field [0001] The invention relates to a microblog emotion classification method based on emotion category description, and belongs to the technical field of natural language processing. Background technique [0002] Microblog sentiment classification is the basis of public opinion analysis. Different from the general sentiment classification that divides the sentiment of the text into subjective and objective or positive and negative, sentiment classification requires the identification of more detailed sentiments in the text, such as happiness, anger, sadness, and fear. Traditional supervised emotion classification methods generally convert categories into numerical labels as supervisory signals to guide the learning process of the model. For example, use "1" for happiness and "2" for anger. Specifically, the digital label will be represented as a one-hot vector, which is used to calculate the training loss, and then minimize the objective function through the b...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/35G06F16/33G06N3/04G06N3/08
CPCG06F16/35G06F16/3344G06N3/08G06N3/047G06N3/045
Inventor 余正涛郭贤伟相艳线岩团郭军军王红斌
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com