Drammar-fused aspect-level text sentiment classification method and system

A technology for sentiment classification and text, applied in text database clustering/classification, semantic analysis, neural learning methods, etc., can solve problems such as ignoring grammatical information, misidentifying key context words, etc., achieve simple models, improve accuracy, and improve The effect of accuracy

Active Publication Date: 2021-08-13
SHANDONG NORMAL UNIV
View PDF16 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Despite significant progress, previous studies usually focus on how to obtain contextual representations based on the semantic associations of constituent words with corresponding aspects, while ignoring grammatical information, which leads to misidentification of key contextual words describing aspects.

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
  • Drammar-fused aspect-level text sentiment classification method and system
  • Drammar-fused aspect-level text sentiment classification method and system
  • Drammar-fused aspect-level text sentiment classification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] This embodiment provides an aspect-level text sentiment classification method that integrates grammar;

[0033] Such as figure 1 As shown, an aspect-level text sentiment classification method that integrates grammar, including:

[0034] S101: Acquiring aspect-level emotional texts to be classified; preprocessing the aspect-level emotional texts to be classified to obtain text information to be classified;

[0035] S102: Input the text information to be classified into the trained deep learning model, and obtain the classification result of the aspect-level emotional text to be classified;

[0036] Among them, the trained deep learning model first performs word embedding processing on the text information to be classified to obtain the text word vector matrix; then, aggregates the text word vector matrix to obtain the hidden state of the text; then, the hidden state of the text Perform weighting processing to obtain a text representation with grammar awareness; then, f...

Embodiment 2

[0098] This embodiment provides an aspect-level emotional text classification system that integrates grammar;

[0099] An aspect-level sentimental text classification system incorporating grammar, including:

[0100] A preprocessing module configured to: acquire aspect-level emotional texts to be classified; perform preprocessing on the aspect-level emotional texts to be classified to obtain text information to be classified;

[0101] The classification module is configured to: input the text information to be classified into the trained deep learning model to obtain the classification result of the aspect-level emotional text to be classified;

[0102] Among them, the trained deep learning model first performs word embedding processing on the text information to be classified to obtain the text word vector matrix; then, aggregates the text word vector matrix to obtain the hidden state of the text; then, the hidden state of the text Perform weighting processing to obtain a te...

Embodiment 3

[0107] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are programmed Stored in the memory, when the electronic device is running, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in Embodiment 1 above.

[0108] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, o...

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 grammar-fused aspect-level text sentiment classification method and system, and the method comprises the steps: carrying out the preprocessing of a to-be-classified aspect-level sentiment text, and obtaining to-be-classified text information; inputting the to-be-classified text information into the trained deep learning model to obtain a classification result of the to-be-classified aspect-level emotion text; performing word embedding processing on to-be-classified text information during classification to obtain a text word vector matrix; performing aggregation processing on the text word vector matrix to obtain a hidden state of the text; weighting the hidden state of the text to obtain text representation with grammar perception; obtaining a dependency vector matrix for the text representation with grammar perception; selecting the most significant feature from the dependency relationship vector matrix; and classifying the most significant features to obtain a classification result. The importance of grammar information on aspect-level sentiment analysis tasks is considered, grammar dependency proximity is converted into weights, and the accuracy of downstream sentiment analysis tasks is improved after the weights are added.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to an aspect-level text sentiment classification method and system fused with grammar. Background technique [0002] The statements in this section merely mention the background technology related to the present invention and do not necessarily constitute the prior art. [0003] With the vigorous development of the Internet, more and more users are willing to share their opinions and experiences on Internet social platforms, online comment information is increasing exponentially, and Internet information is becoming more comprehensive and reliable. Analyzing these comments with emotional polarity can help us quickly understand the views and attitudes of different people on this matter. In recent years, in the field of natural language processing, how to use deep learning technology to analyze the emotional polarity of comment texts on the Internet has become a m...

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): G06F16/35G06F40/253G06F40/284G06F40/30G06N3/04G06N3/08
CPCG06F16/355G06F40/253G06F40/284G06F40/30G06N3/08G06N3/045Y02D10/00
Inventor 刘培玉刘杰朱振方
Owner SHANDONG NORMAL 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