Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Self-supervised public opinion comment viewpoint object classification method based on comparative learning

A classification method and object category technology, applied in neural learning methods, semantic analysis, natural language data processing, etc., can solve problems such as insufficiently clear words in terms of opinion objects, low classification performance of opinion objects, and lack of key terms in Weibo comments. Achieve the effect of enriching semantic information and improving classification effect

Pending Publication Date: 2022-05-27
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a self-supervised public opinion comment object classification method based on comparative learning, which is used for fine-grained classification of microblog sentiment comments, and solves the problem of lack of frequently occurring key terms in microblog comments, or insufficient terms of opinion objects Explicitly address issues that lead to lower performance in opinion object 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
  • Self-supervised public opinion comment viewpoint object classification method based on comparative learning
  • Self-supervised public opinion comment viewpoint object classification method based on comparative learning
  • Self-supervised public opinion comment viewpoint object classification method based on comparative learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Example 1: as figure 1 As shown, a self-supervised public opinion comment opinion object classification method based on contrastive learning, the specific steps of the method are as follows:

[0043] Step 1. Use crawler technology to crawl a number of Weibo comments related to cases in recent years, clean and filter the data, and label the test set and validation set to further verify the model performance.

[0044] Step1.1. Use a crawler based on the Scrapy framework to crawl from Sina Weibo about 60 comments on hot cases with fast spreading speed, high attention and high sensitivity;

[0045] Step1.2. Filter and filter the text and comments of Weibo. The methods of filtering and filtering are as follows: (1) Delete the structure similar to “reply @+username” in Weibo comments, and delete irrelevant hyperlink advertisements (2) ), remove the punctuation after the sentence is divided according to the punctuation, use the jieba word segmentation tool to segment the word...

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 self-supervised public opinion comment viewpoint object classification method based on comparative learning, and belongs to the field of natural language processing. The method comprises the following steps: constructing a data set of microblog comment viewpoint object classification; k-means clustering is carried out on the basis of Word2Vec word vectors, a special self-attention mechanism is fused to obtain vector representation of comments, comment sentence representation is reconstructed, positive and negative examples of comment sentences are constructed through comment sentence word vector representation and sentence representation in the aspect of reconstruction, text features related to comment viewpoint objects are enhanced through a contrastive learning method, and the comment viewpoint objects are obtained. The unrelated distance between the sentences and the non-viewpoint objects is enlarged, so that the comment sentences are deduced and classified through the model. And finally, the comment text is classified into four case aspects: a certain institution, a party, a certain name and others, and support is provided for subsequent microblog comment abstracts.

Description

Technical field [0001] The invention relates to a self-supervised public opinion comment opinion object classification method based on comparative learning, and belongs to the technical field of natural language processing. Background technique [0002] Since news can easily attract public attention on the Internet quickly, and people can express their opinions on the news, causing public opinion to spread, news comment summaries help relevant departments to control the overall situation and fully understand the trends of public opinion. All comments are classified by opinion objects. is a critical step in review summarization. The task of categorizing opinion objects plays an important role in the construction of information platforms. It helps relevant staff understand the subjects of case news comments and effectively retrieve all comment parts of the aspects they are interested in. It also provides aspect-level opinion summarization for the downstream tasks of domain pub...

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 Applications(China)
IPC IPC(8): G06K9/62G06F40/30G06F40/284G06N3/08G06F16/9035G06F16/951
CPCG06F40/30G06F40/284G06N3/088G06F16/9035G06F16/951G06F18/23213G06F18/22G06F18/241Y02D10/00
Inventor 余正涛马梅希
Owner KUNMING UNIV OF SCI & TECH
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
Eureka Blog
Learn More
PatSnap group products