Sentiment classification method of commodity comment data based on convolutional neutral network

A convolutional neural network, commodity review technology, applied in market data collection, electronic digital data processing, natural language data processing and other directions, can solve the problem of ignoring the semantic relationship of words, etc., to enhance the ability of expression, improve classification performance, improve emotion The effect of classification performance

Inactive Publication Date: 2017-11-24
WUHAN UNIV
View PDF3 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] Aiming at the problem that the traditional word vector representation method only extracts lexical features and syntactic features, but ignores the semantic relationship between words, the t

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
  • Sentiment classification method of commodity comment data based on convolutional neutral network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0028] please see figure 1 , a kind of product review data emotion classification method based on convolutional neural network provided by the invention, comprises the following steps:

[0029] Step 1: Use a web crawler to crawl product review data, and mark the sentiment tendency of all review data, labeling positive comments as 1 and negative comments as 0.

[0030] For the convenience of demonstration, this example assumes that 6 items of Jingdong product review data are crawled, and the class labels are marked to form the following review data set:

[003...

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 sentiment classification method of commodity comment data based on a convolutional neutral network. Focusing on the problem that according to traditional word vector representation methods, only vocabulary characteristics and syntax characteristics are extracted, while the semantic relationships among words are ignored, and aiming at the purpose that the classification effects of traditional classification algorithms can be improved, the sentiment classification method of the commodity comment data based on the convolutional neutral network is put forward. Initially the word vector characteristics of each piece of comment data are extracted by means of a CBOW model, the semantic relationships among the words and the representation capability of the word vector characteristics are enhanced, then a sentiment classification model is built by means of the deep learning network model, the convolutional neutral network model, and the sentiment classification performance of the comment data is improved. According to the technical scheme, the method has the advantages of being simple and fast, and the sentiment classification performance of the comment data can be well improved.

Description

technical field [0001] The invention belongs to the technical field of sentiment classification, in particular to a method for sentiment classification of commodity review data based on a convolutional neural network. Background technique [0002] (1) Sentiment classification technology [0003] With the rapid development of mobile network technology and the popularity of smart phones, people tend to buy goods directly on some e-commerce websites through mobile APPs, and users will also post comments on these e-commerce websites to share their purchases. The feeling of using the product after purchasing the product. Sentiment analysis on commodity review data, also called opinion mining, is the process of collecting, preprocessing, and discriminating the emotional tendency expressed by customers on commodity review information. Sentiment classification of review data on e-commerce websites can determine the buyer's emotional tendency for a product: whether he likes the pro...

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): G06F17/27G06F17/30G06Q30/02
CPCG06F16/353G06F40/289G06F40/30G06Q30/0201G06Q30/0203
Inventor 余啸刘进聂国平崔晓晖井溢洋
Owner WUHAN 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