A Construction Method of Sentiment Labeling System

A technology of emotion labeling and construction methods, applied in the direction of semantic tool creation, unstructured text data retrieval, special data processing applications, etc., can solve the lack of word context considerations, only labeling emotional types, not labeling emotional types and emotional strength and other issues to achieve the effects of strong structure, improved readability, and improved scope of application

Inactive Publication Date: 2016-08-31
HEFEI UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, most researchers manually classify texts, and few researches on emotion labeling systems
Manual classification usually only marks one level of text chapters, sentences or words, and most of the text and sentences are emotionally marked only positive, negative and neutral, without marking the precise emotional type and emotional intensity, and emotionally labeling words Lack of consideration of the context of words, only the type of emotion is marked, and the intensity of emotion is not marked

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The construction method of a kind of emotion labeling system of the present invention is to create a new system project in the integrated development environment, the system project comprises the file database that is made of original file database, participle file database and marked file database, utilizes word segmentation tool to the original file database Add separators and parts of speech after all the words in the original file to obtain a word-segmented file composed of the original file, separators and parts of speech, and store the word-segmented file in the word-segmented file database.

[0057] Suppose the original file test1.txt is:

[0058] The first thing I do when I go home in the past few days is to check the news on the Internet and pay attention to the situation of the Sichuan earthquake. I can't help crying again and again, for those poor children, for those parents who are distraught, and for those soldiers who desperately rescued their children. . ...

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 building method of an emotion marking system. The building method of the emotion marking system is characterized by comprising the following steps that (1) an XML source file is newly built in a system project, and chapter nodes, paragraph nodes, sentence nodes and term nodes are added; (2) a foreground window is newly built in the system project, and a button module and an assembly are added; (3) value selection ranges of a conversation emotion marking window and a sentence emotion marking window are set; (4) the file with terms separated is read into a display window; (5) a conversation emotion button and an orderly paragraph serial number button are added into an article structure tree window; (6) the conversation emotion marking window or the sentence emotion marking window is respectively responded; (7) the conversation emotion marking window or the sentence emotion marking window is marked; (8) marking information is written in an XML class to generate an XML marking file of the file with the terms separated. The building method of the emotion marking system can carry out emotion information marking on a test from the three aspects of chapters, sentences and terms, thereby effectively reflecting the emotion type and emotion intensity of the text.

Description

technical field [0001] The invention relates to a construction method of an artificial emotion labeling system, in particular to an emotion labeling system and method for Chinese texts such as blogs and conversations, and belongs to the field of natural language processing and emotion computing. Background technique [0002] Text sentiment analysis is to analyze and mine text information and identify the emotional information in the text. Text sentiment analysis can improve the accuracy of human-computer interaction systems, speech recognition and expression recognition, and is a research hotspot in the field of natural language understanding and emotional computing. In text sentiment analysis, high-quality annotated corpus is an essential research basis. In order to construct higher-quality tagged corpus, the research on emotion tagging system becomes more important. [0003] In the prior art, most researchers manually classify texts, and few researches on emotion tagging...

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 Patents(China)
IPC IPC(8): G06F17/30G06F17/27
CPCG06F16/36
Inventor 全昌勤任福继王丽娟鲍艳伟刘宁
Owner HEFEI UNIV OF TECH
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