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

An Integral Sentiment Intelligent Classification Method for Complex Review Texts Based on Synthetic Deep Capsule Networks

An emotion classification and capsule technology, applied in the field of artificial intelligence, can solve problems such as poor classification effect, achieve the effect of enhancing interpretability and improving accuracy

Active Publication Date: 2022-02-08
WUHAN UNIV
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention proposes an overall emotional intelligent classification method for complex review texts based on a comprehensive deep capsule network, which is used to solve or at least partially solve the technical problem of poor classification effect existing in the methods in the prior art

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
  • An Integral Sentiment Intelligent Classification Method for Complex Review Texts Based on Synthetic Deep Capsule Networks
  • An Integral Sentiment Intelligent Classification Method for Complex Review Texts Based on Synthetic Deep Capsule Networks
  • An Integral Sentiment Intelligent Classification Method for Complex Review Texts Based on Synthetic Deep Capsule Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The inventors of the present application found through a lot of research and practice that the methods in the prior art did not pay attention to the informality of network comment texts, and ignored the noise problems such as misspellings (or abbreviations) and word order errors in these real texts , and the problem of alternate appearance of clauses with different emotional tendencies (mixed emotions), plus the difficulty of grasping the emotional attitude of the review text than simply judging the positive and negative, making them in the complex review text containing such problems Poor performance on sentiment classification.

[0031] Based on the above considerations, according to the logical steps of simulating human reading, the present invention designs an overall sentiment classification method for complex comment texts based on a comprehensive deep capsule network. By capturing feature information at the word level, phrase level and sentence level, the comment ...

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

In order to alleviate the influence of word spelling mistakes, wrong order and mixed emotions on the final grasp of the overall sentiment score of reviews, these noise and mixed emotions can be dealt with in a targeted and orderly manner. The present invention designs a comprehensive deep capsule network classification model , simulating the logical steps of human reading, by capturing feature information at the word level, phrase level, and sentence level, respectively, to model reviews, specifically, modeling at the word level and phrase level with misspelling errors and word order errors Corresponding to the noise problem, the modeling at the sentence level corresponds to the emotional mixing problem, that is, each short sentence is regarded as a synonymy, and the impact of different synonymy groups on the final overall emotional attitude is dynamically considered. In terms of implementation, the BERT WordPiece vector and convolution can be used as word-level and phrase-level features, and then the capsule network can be used to obtain the final vector representation at the sentence level for classification.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an overall emotional intelligence classification method for complex review texts based on a comprehensive deep capsule network. Background technique [0002] As online shopping and consumption have become one of the mainstream lifestyles in today's society, commenting on various products and services on the Internet has become a convenient and effective way for people to publish their satisfaction with products and services, and the amount of user comment data has exploded. growth. How to grasp the attitudes and intentions of users expressed in these review texts plays a vital role in the improvement, marketing and promotion of products and services. However, the comment texts filled in by these users often contain spelling mistakes (or abbreviations), word order errors and other noises and mixed expressions of positive and negative emotions and attitudes, which ...

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): G06F16/35G06N3/04G06N3/08
CPCG06F16/35G06N3/08G06N3/045
Inventor 韩波张靓
Owner WUHAN 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