E-commerce comment sentiment analysis model based on part-of-speech features and viewpoint features in combination with convolutional neural network

A convolutional neural network and sentiment analysis technology, applied in the field of e-commerce review sentiment analysis models, can solve problems such as inconsistencies in ratings, and achieve the effect of improving sentiment analysis performance

Pending Publication Date: 2020-09-22
HARBIN UNIV OF COMMERCE
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above technical problems, the purpose of the present invention is to provide an e-commerce review sentiment analysis model based on part-of-speech features and opinion features combined with convolutional neural network, to solve the problem of inconsistency between reviews and their ratings, and then help merchants improve service quality and upgrade product performance

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
  • E-commerce comment sentiment analysis model based on part-of-speech features and viewpoint features in combination with convolutional neural network
  • E-commerce comment sentiment analysis model based on part-of-speech features and viewpoint features in combination with convolutional neural network
  • E-commerce comment sentiment analysis model based on part-of-speech features and viewpoint features in combination with convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] Sample hotel review: It was a surprise to me to live in such a room at this price. The business double room I booked is very spacious and comfortable, and the study in the room is very good.

[0061] 1. Feature extraction

[0062] The text features of this model mainly include part-of-speech features and opinion features.

[0063] The part-of-speech feature is extracted through the part-of-speech tagging function of ltp, and the result of the part-of-speech feature of the example is: this / rprice / n live / v to / v such / r's / u room / n is to / p me / r is / u It is / v surprise / a, / u business / n big bed room / n very / d spacious / a comfortable / a, / wp room / n inside / nd of / u business / n very / d nice / a. / wp

[0064]Opinion features are extracted through the rules formulated by the results of dependency syntax analysis and semantic dependency analysis. The example opinion feature results are: this-other price-evaluation object living-opinion word to-other such-other-other room-other pair- Oth...

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 an e-commerce comment sentiment analysis model based on part-of-speech features and viewpoint features in combination with a convolutional neural network. The method comprisesthe following steps: step 1, formulating rules by utilizing part-of-speech, dependency grammar analysis and semantic dependency analysis to extract viewpoint features; step 2, introducing part-of-speech features and viewpoint features by adopting a vector splicing method on the basis of word vector representation; and step 3, taking a word vector and an extended feature vector as two input channels of a convolutional neural network to perform sentiment analysis. The problem that comments are inconsistent with scores of the comments is solved, and then merchants are helped to improve the service quality and upgrade the product performance.

Description

technical field [0001] The invention relates to the technical field of e-commerce reviews, in particular to an e-commerce review sentiment analysis model based on part-of-speech features and opinion features combined with a convolutional neural network. Background technique [0002] With the rapid popularization of the Internet, more and more industries have shifted from offline to online. Among them, the e-commerce industry is developing rapidly with the number of users and transaction volume increasing year by year. Due to the online sales characteristics of e-commerce, users usually give feedback on their purchase experience in the form of text comments. The content not only extracts suggestions for merchants, but also provides references for other customers, which has extremely high commercial and social value. , but this kind of data has the characteristics of small space and weak standardization. How to obtain the emotional tendency contained in the evaluation informat...

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): G06F16/35G06F40/211G06F40/253G06F40/30G06N3/04
CPCG06F16/353G06F40/211G06F40/253G06F40/30G06N3/045
Inventor 张艳荣孙家媛赵志杰孟令跃
Owner HARBIN UNIV OF COMMERCE
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