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

Chinese comment-oriented sentiment multi-tendency classification method

A classification method and emotion technology, applied in text database clustering/classification, text database query, unstructured text data retrieval, etc., can solve problems such as difficult to deal with emotional classification

Active Publication Date: 2021-06-01
ZHEJIANG WANLI UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing research on the classification of comment sentiment tendencies mainly divides sentiment tendencies into positive emotions, negative emotions, and neutral emotions. Disapprove, strongly disapprove, etc. These classifications divide emotional tendencies into several fixed types, and it is difficult to deal with more complex emotional classification situations

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 comment-oriented sentiment multi-tendency classification method
  • Chinese comment-oriented sentiment multi-tendency classification method
  • Chinese comment-oriented sentiment multi-tendency classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0051] Such as figure 1 As shown, the present invention provides a kind of emotion multi-inclination classification method for Chinese comments, comprising the following steps:

[0052] First, morpheme sentiment variables are extracted. According to the existing Chinese morpheme lexicon and emotion corpus lexicon, various morpheme words and emotion words about the commented object in the comment text are extracted. According to the characteristics of Chinese language to describe things, the Pearson correlation coefficient method is used to calculate the correlation coefficient between morpheme words and emotional words, and the morpheme emotion variables are composed of correlation coefficients. This morpheme emotion variable can be used as an independent emotion content to describe a certain emotion type, and it can be regarded as an independent emot...

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 Chinese comment-oriented sentiment multi-tendency classification method, which comprises the following steps of: firstly, extracting morpheme words and sentiment words; secondly, constructing a similarity relationship between morpheme emotion variables; and finally, calculating a morpheme emotion close path. According to the method, morpheme emotion variables are regarded as nodes in a directed weighted acyclic graph, directed weighted relation connection is constructed between morpheme emotion nodes to serve as directed weighted link edges, and on the basis of the directed weighted link edges, an effective path meeting a certain weight condition is searched. According to the method, a directed weighted acyclic graph model is combined with emotion tendency analysis, emotion multi-tendency classification of comments is achieved through three steps of extracting various morpheme emotions of the comments, analyzing similarity relationships among the morpheme emotions and calculating a morpheme emotion close path, various attitudes expressed by a user to things are more accurately distinguished, and the opinions of the users on object attributes and features are reflected.

Description

technical field [0001] The invention relates to the classification of emotional tendencies, in particular to a method for classifying emotions with multiple tendencies for Chinese comments. Background technique [0002] With the rapid promotion and development of applications such as blogs, microblogs, and comments, various comments on the Internet have become an important way for users to express their opinions and communicate online. Comment information on the Internet usually expresses users' views on things in the form of short texts, such as comments on news events, comments on commodity performance, and so on. All these comments are posted by a large number of users, who put forward their own views and propositions on things from different sides and different angles. As these evaluation information accumulate over time, a data set with complex structure, diverse content and mixed emotions is formed. [0003] Relevant comments made by users on things they are interest...

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): G06F16/33G06F16/35G06F40/284
CPCG06F16/3344G06F16/35G06F40/284
Inventor 张少中
Owner ZHEJIANG WANLI UNIV
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