Semantic-based Chinese network text emotion extracting method

A network text and emotion technology, applied in special data processing applications, instruments, electronic digital data processing, etc., can solve the problems of low recognition rate, lack of emotional information in Chinese text, and restrict the development of Chinese human-computer emotional interaction, etc., to achieve high The effects of universality, effective extraction, and detailed analysis

Inactive Publication Date: 2011-07-13
BEIHANG UNIV
View PDF0 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In terms of research on the emotional information of Chinese language texts, most of the current research is limited to the two emotional polarities of praise and criticism, and there is a lack of corresponding models for network language processing, which greatly restricts the development of Chinese human-computer emotional interaction.
The text processing model for Internet language combined with the emotion extraction method of six basic emotion models of Ekman can effectively solve the problems of lack of emotional information and low recognition rate in Chinese texts.

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
  • Semantic-based Chinese network text emotion extracting method
  • Semantic-based Chinese network text emotion extracting method
  • Semantic-based Chinese network text emotion extracting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to more clearly illustrate the purpose, technical solutions and advantages of the present invention, the network text emotion recognition methods of the three embodiments will be further described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0044] The basic idea of ​​the present invention is to obtain the basic component relationship of the sentence by performing grammatical and semantic preprocessing on the network text; according to the artificially marked emotional corpus, the corresponding components are assigned emotional vectors; and finally through the defined emotional rules. Get the sentiment vector of the sentence.

[0045] According to the above idea, the flow chart of the present invention is shown in Fig. 1 .

[0046] The method for recognizing network text emotion will be des...

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 provides a method capable of accurately extracting network text emotion information. The method comprises the following steps of: (1) detecting special symbols such as emotion symbols, abbreviations, acronyms, interjections and the like in a text; (2) pre-processing the plain text by using a professional syntax analyzer to obtain a basic syntactic relationship of sentences; (3) analyzing words separated from the sentences, and endowing the words with emotion vectors; (4) obtaining phrase emotion vectors according to the types of different phrases and the corresponding emotion rules; and (5) obtaining final emotion vectors of the sentences according to different types of the sentences by combining the phrase emotion vectors. The network text emotion extracting method can comprehensively and detailedly identify the emotion types, and has high accuracy.

Description

(1) Technical field [0001] The invention relates to a method for extracting network text emotion information, and mainly relates to the fields of natural language processing and emotion computing. (2) Background technology [0002] Natural language is one of the unique means of communication for human beings, and with the development of the Internet, natural language has also become an important means of network communication, and gradually derived a new language method: Internet language. Network text information contains rich emotional information, corresponding to the corresponding psychological state of the user, so the research on text emotion extraction is of great significance in the field of emotional computing and intelligent interaction. It enables the computer to experience human emotions and make appropriate responses from text information, and can be used in man-machine dialogue systems and bionic agent interaction systems. How to accurately and effectively rec...

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 毛峡江琳
Owner BEIHANG 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