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

Short text aspect-level sentiment classification method

A technology of emotion classification and short text, applied in text database clustering/classification, unstructured text data retrieval, instruments, etc., can solve the problem of not being able to recognize emotions in a fine-grained manner

Active Publication Date: 2021-02-09
HEFEI UNIV OF TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most of the sentiment classifications for short texts are coarse-grained classifications, that is, only one sentiment classification is given for short texts, and the sentiments corresponding to different aspects cannot be fine-grained.

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
  • Short text aspect-level sentiment classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] In the present embodiment, a kind of emotion classification method of the Bilstm model that fuses word vector and aspect vector, part-of-speech vector, and adds Attention mechanism is to carry out as follows:

[0042] Step 1. Obtain all short texts in the comment data and use them as a corpus, perform preprocessing operations such as classification, cleaning, and word segmentation on any short text in the corpus, and obtain the word segmentation set of the corresponding short text, which is recorded as t=(t 1 ,t 2 ,...,t i ,...,t k ), t i Represents the i-th word, i∈[1,k], k represents the total number of words in the short text;

[0043] Step 2, pair word vector set t=(t 1 ,t 2 ,...,t i ,...,t k ) for part-of-speech recognition, and obtain the part-of-speech representation vector set p″’=(p″’ 1 ,p″' 2 ,...,p″′ i ,...,p″′ k ), p″' i represents the i-th word t i the corresponding part of speech;

[0044] Step 3. Perform preprocessing operations on all short...

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 short text aspect-level sentiment classification method, which comprises the following steps of: 1, performing word segmentation on a short text, generating word vectors through words in the short text, and labeling all aspect vectors and part-of-speech vectors; 2, judging the owned aspects of the short text by using an XLNET model, and splicing the word vector, the part-of-speech vector and the owned aspect vector of each word in sequence; 3, inputting the vector formed by splicing the words in the step 2 into an emotion classification Bilstm model, inputting the obtained implicit vector of each word into an Attention mechanism, and returning the weight of the implicit vector of each word; and 4, performing weighted average by using the implicit vector and the weight corresponding to each word, enabling a result to enter a softmax neural network to obtain a corresponding sentiment, and taking a relatively high probability value as a sentiment classification result. Fifferent sentiments of the short text in different aspects can be recognized, so that fine-grained sentiment classification is completed.

Description

technical field [0001] The invention belongs to the field of natural language processing in artificial intelligence, and specifically relates to an emotion classification method of a Bilstm model that integrates word vectors, aspect vectors, and part-of-speech vectors, and adds an Attention mechanism. Background technique [0002] With the development of e-commerce platforms, short text comments have increasingly become an important way for users to express their emotions. However, more than one aspect is often involved in short texts, and even opposite emotional attitudes may be held for different aspects. At present, most of the sentiment classifications for short texts are coarse-grained classifications, that is, only one sentiment classification is given for short texts, and the sentiments corresponding to different aspects cannot be fine-grained. Contents of the invention [0003] In order to solve the shortcomings of the above-mentioned prior art, the present invent...

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): G06F16/35G06F40/289G06K9/62
CPCG06F16/35G06F40/289G06F18/214
Inventor 倪丽萍高九洲朱旭辉陈星月
Owner HEFEI UNIV OF TECH
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