Text sentiment classification method and system

A technology of emotion classification and text, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of low accuracy rate of classification results, and achieve the effect of avoiding adverse effects and improving accuracy rate

Active Publication Date: 2012-09-19
SUZHOU UNIV
View PDF5 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a text sentiment classification method, which has solved the problem of low correct rate of classification results of existing text sentiment classification methods

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
  • Text sentiment classification method and system
  • Text sentiment classification method and system
  • Text sentiment classification method and system

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0063] Example 1: I don't like this product.

[0064] In the sentence of example 1, if the emotional word is "like", and the keyword "no" with a negative structure appears in this sentence, then the polarity of the emotional word "like" has changed.

[0065] 2) Polarity transition rules based on modal structure:

[0066] Modality is related to the attitude of the reviewer, which is close to his / her expression in terms of degree of certainty, degree of reliability, degree of subject, degree of information source, and degree of opinion, which belongs to the category of sentiment classification research.

[0067] The polarity transition rule based on the modal structure is: if in the sentence where the emotional word is located, the keyword of the preset modal structure appears in front of the emotional word, then the polarity transition occurs in the emotional word; The rule is described below in combination with specific examples.

[0068] ①A sentence expresses the reviewer's...

example 2

[0069] Example 2: I used to think it was of good quality.

[0070] In the sentence of example 2, if the emotional word is "very good", and the keyword "ever" in the modal structure appears before the emotional word "very good", it means that this emotion expresses the past thoughts, not the present Thoughts, then the emotional word "very good" undergoes a polarity change.

[0071] ②A sentence describes a hypothetical situation or the expression of emotion in a conditional hypothetical sentence is a hypothetical situation, for example:

example 3

[0072] Example 3: It would be nice if the color was red.

[0073] In the sentence of example 3, if the emotional word is "good", and in the sentence, the keyword "if" of the modal structure appears in front of the emotional word "good", then the polarity of the emotional word "good" has changed .

[0074] ③The expression statement of a sentence is indeterminate, for example:

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 embodiment of the invention discloses a text sentiment classification method, which comprises the steps of finding a sentiment word in a text to be classified by referring to a preset sentiment word list, and acquiring a sentiment polarity corresponding to the sentiment word according to the sentiment word; utilizing two polarity conversion rules to judge whether the sentiment word has polarity conversion or not, and calculating probability of each word in the text to be classified appearing in the text of each polarity according to the sentiment polarity of the sentiment word and the polarity conversion result of the sentiment word; and utilizing a Bayes classifier model to classify the text to be classified according to the probability of each word appearing in the text of each polarity. According to the classification method, the classification effect is far higher than that of a traditional text sentiment classification method, the unfavorable influence of the sentiment word having the sentiment polarity conversion on the classification effect of the text can be avoided, and the classification accuracy of the text sentiment can be improved.

Description

technical field [0001] The present invention relates to the fields of natural language processing technology and pattern recognition, and more specifically, relates to a text sentiment word classification method and system. Background technique [0002] With the general development of Internet applications, a large number of users participate in the Internet (such as blogs, forums, etc.) to generate comments on people, events, products, etc., and these comments express various emotions and emotional tendencies of users. This not only provides a platform for merchants to display information, but also provides a platform for consumers (ie users) to exchange product experience. How to extract this type of text with emotion from these massive texts, and analyze and research the text emotion, has a strong application value. For example, users can understand the information of the product based on the product’s comments and choose the appropriate product. ; Merchants improve the ...

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): G06F17/30G06F17/27
Inventor 李寿山张小倩周国栋
Owner SUZHOU 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