Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for automatically constructing emotional dictionary for commodity reviews

A product review and sentiment dictionary technology, applied in business, natural language data processing, semantic analysis, etc., can solve problems such as the difficulty of constructing domain sentiment dictionaries

Active Publication Date: 2018-11-06
HOHAI UNIV
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Fast found that it is very difficult to build domain sentiment lexicons by using information experts or crowdsourcing services

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
  • Method for automatically constructing emotional dictionary for commodity reviews
  • Method for automatically constructing emotional dictionary for commodity reviews
  • Method for automatically constructing emotional dictionary for commodity reviews

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039]Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0040] At first, for the convenience of understanding the present invention, make following explanation:

[0041] 1. Text preprocessing:

[0042] The text preprocessing module mainly preprocesses the original comment text, such as figure 1 As shown, for Chinese, Chinese word segmentation is required, and there are many open source software that can be used for Chinese word segmentation, such as jieba word segmentation software, ik word segmentation device, etc. If you want to achieve the best wor...

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 method for automatically constructing an emotional dictionary for commodity reviews, containing text preprocessing, semantic relationship mining, and emotional word clustering, wherein the text preprocessing is used to preprocess commodity reviews and extract emotional words and evaluation objects contained in a certain category of product reviews; the semantic relationship mining is used to mine the semantic relationship between the emotional words and evaluation objects, and use the form of matrix to represent the semantic relationship between the emotional words and evaluation objects; and the emotional word clustering is used to performing unsupervised clustering on the emotional words according to the mutual distance of the emotional words in the emotional matrix space so as to reasonably classify the emotional words into k categories. The invention constructs a domain sentiment dictionary aiming at the characteristics of the text in the field of commodity review, which may classify the emotional words into multiple categories instead of traditional praise and disparage categories. For commodity review fields, domain sentiment dictionaries have greatadvantages compared with other current general sentiment dictionaries in the emotional classification task and other aspects.

Description

technical field [0001] The invention relates to a self-defined construction method of an emotional dictionary aimed at the field of commodity reviews, and belongs to the technical field of computer information technology processing. Background technique [0002] With the development of various shopping websites, a large number of comments about various commodities have appeared on the Internet, and people can check these comments anytime and anywhere. And identifying the emotional tendencies contained in these comments is very important for both merchants and consumers. And a good sentiment dictionary is the basis for text sentiment analysis. As we all know, performing sentiment analysis on text needs to consider the industry domain to which the text belongs. However, the existing sentiment dictionaries are all general, and there is no sentiment dictionary for the specified field of commodity reviews. Obviously, it is inappropriate to use traditional sentiment lexicons to...

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): G06F17/27G06Q30/02
CPCG06Q30/0282G06F40/289G06F40/30
Inventor 冯钧贡诚李晓东邹希
Owner HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com