Comment text aspect-level sentiment classification method and system based on deep learning

A technology of emotion classification and deep learning, applied in the field of consensus algorithm, can solve problems such as misleading customers and affecting customer judgment

Pending Publication Date: 2020-10-30
上海哈蜂信息科技有限公司
View PDF0 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If we simply judge the emotional polarity of a sentence,

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
  • Comment text aspect-level sentiment classification method and system based on deep learning
  • Comment text aspect-level sentiment classification method and system based on deep learning
  • Comment text aspect-level sentiment classification method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] In order to realize fine-grained sentiment analysis at the comment text level, with the help of existing neural network technology, the present invention adds the preprocessing of neural network weights before neural network training. In the calculation process of the neural network, the essence of its forward propagation is matrix multiplication, and the essential form of the parameters in the neural network is a parameter matrix. A fully connected neural network such as image 3 shown.

[0067] A fully connected neural network consists of three layers: input layer, hidden layer, and output layer. Among them, the input layer represents the input data, which is represented by a vector x, and in the above figure, x∈3×1 is a column vector. The hidden layer represents the weight layer of the neural network, which contains the hidden layer weights, with image 3 For example, the hidden layer weight is w∈4*3. In the previous calculation of the neural network, the data fl...

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 provides a comment text aspect-level sentiment classification method based on deep learning. The method comprises the following steps: preprocessing a comment text, including word segmentation and stop word removal, balancing aspect words and corresponding tags to generate a balanced sample, and vectorizing the balanced sample and Chinese words in an original sample to obtain word vectors in the balanced sample; inputting the word vectors into the model to predict a comment result, wherein the model is a deep learning model constructed according to a deep neural network, the similarity calculation is carried out on word vectors of aspect words and other words of sentences, and an aspect emotion semantic matrix of a balance sample is generated. According to the method, throughthe balance processing and construction of the Attn-Bi-LCNN model, the emotion semantic matrix can be effectively output, and the accuracy of the model and the prediction speed in practical application are improved, so the method is suitable for aspect-level fine-grained emotion classification of texts.

Description

【Technical field】 [0001] The present invention relates to a consensus algorithm of deep learning in the field of natural language processing, especially a method for aspect-level sentiment classification of comment text based on deep learning, and also relates to a system for realizing the method. 【Background technique】 [0002] In today's big data era, a large amount of data is generated every day. The popularity of the Internet not only makes the connection between people closer, but also makes the connection between people and information more frequent. The emergence of the Internet not only makes the dissemination of information more convenient, but also stimulates people's desire to share information, especially today's young people are more willing to express their emotions by expressing their opinions on various social media and portal websites . Mining such a large number of blogs, microblogs, product evaluations and thing reviews that contain personal emotions can...

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): G06F16/35G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F16/35G06F40/30G06N3/08G06N3/045G06F18/214
Inventor 刘文远郭智存于家新付闯
Owner 上海哈蜂信息科技有限公司
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