Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Model training method for cross-domain sentiment analysis based on convolutional neural network

A technology of convolutional neural network and sentiment analysis, which is applied in the field of cross-domain sentiment analysis model training, can solve problems such as poor classification effect, and achieve the effect of reducing labeling

Active Publication Date: 2019-05-14
DALIAN NATIONALITIES UNIVERSITY
View PDF9 Cites 67 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The researchers found that in sentiment classification, the classification effect is poor on data sets that belong to different fields for the training set and the test set.

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
  • Model training method for cross-domain sentiment analysis based on convolutional neural network
  • Model training method for cross-domain sentiment analysis based on convolutional neural network
  • Model training method for cross-domain sentiment analysis based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0061] 1.1 Solve the problem

[0062] The present invention proposes a method based on neural network model migration to solve the problem of cross-domain sentiment analysis. Commonly used sentiment classification research methods include processing Chinese and English corpus, data vector representation, feature extraction, and classification. Explain the method and use of the data preprocessing model, and introduce the relevant mathematical principles and framework of Word2vec, verify that the use of depth migration method can effectively solve the learning effect on different tasks, the deep network framework used in the present invention is in CNN convolution Transfer based on the neural network model. Model migration is performed on cross-domain emotional texts, and fine-truning is performed on existing models in the target domain to solve the problem of cross-domain sentiment analysis.

[0063] 2.1 Sentiment Analysis

[0064] 2.1.1 Basic concepts

[0065] Text sentimen...

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 model training method for cross-domain sentiment analysis based on a convolutional neural network, belongs to the field of cross-domain sentiment classification, and aims tosolve the problem of cross-domain sentiment analysis. The method comprises: S1, preprocessing a text; S2, training a word vector model; S3, performing cross-domain model migration; wherein the step S3is carried out in sequence; a neural network model is trained through a source domain; migrating the trained model. Firstly, a weight value of a convolution kernel in a model is shared, a convolutionkernel weight trained in a source domain is used for extracting corresponding features in a target domain, a small part of data in the target domain is trained again, parameters of a full connectionlayer weight of the previously trained model are adjusted, and the effect is that model migration is conducted on a cross-domain emotion text.

Description

technical field [0001] The invention belongs to the field of cross-domain emotion classification, and relates to a model training method for cross-domain emotion analysis based on a convolutional neural network. Background technique [0002] In machine learning algorithms and data mining algorithms, an important assumption is that the training data and future training data must be in the same feature space and have the same data distribution. However, such an assumption does not hold true in practical application cases. Therefore, when the data distribution changes, most statistical models need to be reconstructed using training samples of the new data. In practical applications, the amount of data generated every day is unbelievable. According to the current data generation speed, 2.5 terabytes of data will be generated every day. If the data is collected again and the model is reconstructed, it will take At a very large cost, this is obviously impossible. Moreover, the ...

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): G06F16/35G06F17/27G06K9/62
Inventor 孟佳娜于玉海
Owner DALIAN NATIONALITIES UNIVERSITY
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
Eureka Blog
Learn More
PatSnap group products