Method capable of simultaneously filtering irrelevant comments and carrying out sentiment classification on relevant comments

A sentiment classification and sentiment technology, applied in text database clustering/classification, semantic analysis, instruments, etc., can solve problems such as document distance representation

Pending Publication Date: 2020-02-28
TIANJIN UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since similar words may be in different positions in the two texts, it is not possible to simply use the distance between words in the corresponding positions of the two short texts to represent the distance of the document

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
  • Method capable of simultaneously filtering irrelevant comments and carrying out sentiment classification on relevant comments
  • Method capable of simultaneously filtering irrelevant comments and carrying out sentiment classification on relevant comments
  • Method capable of simultaneously filtering irrelevant comments and carrying out sentiment classification on relevant comments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0102] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. Taking the analysis of user satisfaction as an example to illustrate the specific implementation process of the present invention:

[0103] A method capable of simultaneously filtering irrelevant comments and performing sentiment classification on related comments, the method comprising the following steps:

[0104] 1) Preprocessing the short text;

[0105] Step 1) of the present invention is specifically:

[0106] (7) Crawl the comment data of the target website to form the corpus in the experiment;

[0107] (8) Remove irrelevant symbols and punctuation marks in the corpus. ? ! ,,;: ""''()-... "";

[0108] (9) Use a word segmentation tool to perform word segmentation processing on the obtained comment data;

[0109] (10) remove irrelevant stop words in the corpus after word segmentation;

[0110] (11) Carry out emotional labeling to each...

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 discloses a method capable of simultaneously filtering irrelevant comments and carrying out sentiment classification on relevant comments, which mainly comprises the following steps of:firstly, preprocessing a short text; secondly, training a word vector by utilizing an HSSWE model; thirdly, obtaining the distance between the documents through a WMD model; and finally, classifying the target documents by utilizing a classifier. And the satisfaction degree of the masses can be accurately obtained by utilizing a short text type discrimination and emotion technology, so that the method has important significance for making subsequent policies. Compared with the prior art, the method has the obvious advantages that irrelevant texts can be automatically filtered out when the emotion of the short text is judged, and the precision of a classification algorithm is improved.

Description

technical field [0001] The invention belongs to the field of computer natural language processing, and specifically relates to a method capable of simultaneously filtering irrelevant comments and performing emotion classification on related comments. Background technique [0002] With the development of society and computer technology, people are more inclined to express their opinions on the Internet. Timely acquisition and mining of people's opinions is of great significance to the control of public opinion and the improvement of products. In the existing technology, when classifying text sentiment, in most cases, no processing is done on irrelevant comments, which will cause a loss of precision in statistical results. The present invention is a technology capable of simultaneously filtering irrelevant comments and sentiment classification of related comments, mainly involving two technologies of sentiment classification and short text category division. The current devel...

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): G06F40/30G06F40/289G06F16/35
Inventor 沈幸博孙越恒
Owner TIANJIN UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap