Deep transfer learning method for text sentiment classification

A technology of sentiment classification and transfer learning, applied in the field of text learning, can solve the problem of low accuracy of text sentiment classification, and achieve the effect of improving adaptability and high classification accuracy

Inactive Publication Date: 2020-09-18
NORTHWEST NORMAL UNIVERSITY
View PDF2 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The accuracy of deep learning for text sentiment classification is extremely low when there is not enough labeled data to train the network model

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
  • Deep transfer learning method for text sentiment classification
  • Deep transfer learning method for text sentiment classification
  • Deep transfer learning method for text sentiment classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0041] Algorithm thought of the present invention:

[0042] The convolutional neural network contains a large number of parameters to be trained. At the beginning of training, these parameters are usually initialized randomly, which makes the initial error of the network larger, which easily leads to poor network convergence and over-fitting problems. Aiming at this problem, a supervised pre-training method of transfer learning based on feature selection is proposed. The purpose is to obtain the common feature representations in the source domain and the target domain, and then realize knowledge tr...

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 deep transfer learning method for text sentiment classification, which comprises the following steps: source domain pre-training: selecting large-scale data as a source domain training sample, and training a convolutional neural network in a supervised manner for a target recognition task to obtain a pre-training model; feature information migration, and constructing a convolutional neural network with the same structure as the pre-training model, taking small-scale text data as a target task of a target domain, initializing parameters of a corresponding layer of thenetwork by utilizing all layer parameters except a full connection layer in the pre-training model obtained in the previous step, and performing fine adjustment on the network by taking the target data as a training sample. According to the method, feature information migration from the source domain to the target domain is achieved, a remarkable effect is achieved in an emotion classification task, high classification accuracy is obtained, and the adaptability of the model is improved.

Description

technical field [0001] The invention relates to a text learning method, in particular to a deep transfer learning method for text sentiment classification. Background technique [0002] With the vigorous development of information technologies such as mobile Internet, social networks, and e-commerce, website comment areas, Weibo, and major e-commerce platforms have become important carriers for Internet users. How to efficiently and reasonably process, analyze and utilize text comment information on such platforms is a topic of widespread concern to researchers. Sentiment classification refers to dividing the text into positive or negative types according to the meaning and emotional information expressed in the text, and it is the division of the author's tendency, viewpoint and attitude. Therefore, it has important research significance for public opinion monitoring. [0003] Traditional sentiment classification methods include dictionary-based methods and machine learni...

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): G06F16/35G06N3/04G06N3/08
CPCG06F16/355G06N3/084G06N3/045G06N3/044
Inventor 代祖华牟巧玲李泓毅王玉环
Owner NORTHWEST NORMAL 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
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