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

Chinese long text sentiment analysis method

A sentiment analysis, long text technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problem of low accuracy, and achieve the effect of improving efficiency, improving recall rate, and improving accuracy rate

Inactive Publication Date: 2019-08-06
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the problem of low accuracy of existing long text sentiment analysis algorithms, and provide a long text sentiment analysis method based on machine learning, which uses conditional random field to extract core sentences and introduces sentence sentiment polarity weights for analysis Entire article, improve the accuracy of Chinese long text sentiment analysis

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
  • Chinese long text sentiment analysis method
  • Chinese long text sentiment analysis method
  • Chinese long text sentiment analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] figure 1 It is a flow chart of a Chinese long text sentiment analysis method of the present invention.

[0053] In this example, if figure 1 Shown, a kind of Chinese long text emotion analysis method of the present invention comprises the following steps:

[0054] S1. Conditional random field extraction of core sentences

[0055] For each input sentence, the conditional random field model is used to mark the evaluation object, and the word with the most occurrences in the entire article is counted as the evaluation object of the entire article, and the sentence containing the evaluation object is extracted as the core sentence. To perform word segmentation and remove stop words on the core sentence, different word segmentation methods can be adopted for different languages. In this embodiment, the Jieba Chinese word segmentation system is used for Chinese word segmentation. After obtaining the part of speech, remove punctuation marks, onomatopoeia, interjections, aux...

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 Chinese long text sentiment analysis method. The method comprises the steps of 1, preprocessing a text; 2, extracting a core sentence from a conditional random field; step 3,performing sentiment analysis on the core sentence; 4, defining an emotion polarity weight of the core sentence; 5, expanding an emotion dictionary used by the current emotion analysis; 6, obtaininga final emotion analysis result. The core sentences are extracted through the conditional random field, and the sentence emotion polarity weights are introduced to analyze the whole article, so that the Chinese long text emotion analysis accuracy is improved.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a method for sentiment analysis of long Chinese texts. Background technique [0002] In the past few decades, people's lives have been increasingly inseparable from the Internet. With the development of "Internet +", many traditional industries have been combined with the Internet, and the Internet is gradually changing people's lifestyles. The current users have From simple seekers of information obtained from the Internet to creators of Internet information, people express their ideas and opinions through Weibo, circle of friends, and forums. In recent years, information on the Internet has also shown exponential growth. [0003] This information often has huge social and economic benefits. For individuals, knowing other people’s views can help them make choices in shopping or learn knowledge they don’t know; for businesses or organizations, it can help them understa...

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): G06F17/27
CPCG06F40/289G06F40/30
Inventor 王雄张磊任婧徐世中王晟
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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