Sentiment classification method based on polarity transfer rules

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

Inactive Publication Date: 2012-01-18
SUZHOU UNIV
View PDF0 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the sentence "I do not like this boot at all." contains a positive sentiment word "like", but the sentiment polarity of the whole sentence is negative. It can be seen that the classification method obtained by using the word count The accuracy of the classification result is not high

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
  • Sentiment classification method based on polarity transfer rules
  • Sentiment classification method based on polarity transfer rules
  • Sentiment classification method based on polarity transfer rules

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0041] Example 1: This hotel is too far and it is not cheap to call ataxi.

[0042] The hotel is more inconvenient to take a taxi.

[0043] In the sentence of Example 1, if the emotional word is "cheap" and the functional negative keyword "not" appears in the sentence, then the polarity shift of the emotional word "cheap" occurs, and Example 1 is a functional negation.

example 2

[0044] Example 2: This hotel lacks efficient management.

[0045] The hotel lacks effective management.

[0046] In the sentence of Example 2, if the emotional word is "efficient", and the contextual negative keyword "lack" appears in the sentence, and the emotional word "efficient" and the contextual negative keyword "lack" are two adjacent words , that is, there are no more than 5 words between them, then the emotional word "efficient" has undergone a polarity shift, which is contextual negation in this case.

[0047] 2. Polarity transfer rules based on turning structure;

[0048] Turning structure is a special type of transformation, which can be used to express the contradictory and contrasting relationship between paragraphs, sentences, clauses, and words. It is distinguished from other types of conversion structures by different keywords. The transition keywords of the transition structure such as: however, but and so on.

[0049] An obvious difference between the ne...

example 3

[0051] Example 3: This hotel is good in its equipments, but it lacks efficient management.

[0052] The hotel has good facilities but lacks effective management.

[0053] In the sentence of Example 3, if the emotional word is "good" and the turning keyword "but" appears in the sentence, that is, in the second half of the sentence, then the polarity of the emotional word "good" has shifted.

[0054] 3. Polarity transfer rules based on voice structure;

[0055] Voice is related to the attitude of the reviewer, which approximates the degree to which he / she expresses in terms of certainty, reliability, subjectivity, source of information, and degree of opinion. Voice structure is also a very common structure that causes polarity shift, and it belongs to the category of emotion classification research.

[0056] The content of the polarity transfer rule based on the voice structure is that if there is a voice key word before the emotional word in the sentence where the emotional w...

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 sentiment classification method based on polarity transfer rules, comprising the following steps of: finding out sentiment words from a text to be classified, and obtaining corresponding sentiment word polarity of the sentiment words; using two or more polarity transfer rules to judge whether the polarity of the sentiment words is transferred, wherein the polarity transfer rules include the polarity transfer rule based on a negative construction, or the polarity transfer rule based on a transition construction, or the polarity transfer rule based on a voice construction, or the polarity transfer rule based on an implied construction; calculating the sentiment polarity of the text to be classified according to the obtained sentiment word polarity and the polarity transfer judging result; and classifying the text to be classified according to the sentiment polarity of the text to be classified. The method avoid the negative influence of the sentiment words with transferred polarity on the text classification result, and is good for improving classification effect of the text.

Description

technical field [0001] The present invention relates to the technical field of natural language processing and the field of pattern recognition, and is an emotion classification method based on polarity transfer rules. Background technique [0002] With the rapid development of the Internet, the information on the Internet is becoming more and more abundant. How to analyze information from massive data and extract useful information is a key issue. In real life, people are becoming more and more accustomed to expressing their opinions and emotions on the Internet. There are a large number of texts with emotions on the Internet. Such texts often exist in the form of product reviews, forum comments, and blogs. Can reflect people's views and opinions very well. Extracting this type of text with emotion from these massive texts, and analyzing and researching text emotion on it, has strong application value. Brands; merchants improve the quality of products based on user commen...

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): G06F17/30G06F17/28
Inventor 李寿山钱龙华周国栋
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