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

New sentiment word extraction method based on commodity comments

An extraction method and technology of emotional words, applied in the field of text analysis, can solve the problems of undiscovered emotional words and insufficient recognition ability of new emotional words, and achieve the effect of reasonable judgment, high accuracy and scale expansion.

Active Publication Date: 2020-06-09
ANHUI UNIV OF SCI & TECH
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the fact that traditional general dictionaries are not capable of recognizing new emotional words, that is, some new and niche emotional words have not been discovered, the present invention proposes a method for extracting new emotional words based on commodity reviews

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
  • New sentiment word extraction method based on commodity comments
  • New sentiment word extraction method based on commodity comments
  • New sentiment word extraction method based on commodity comments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The method for extracting new emotion words provided by the present invention will be further explained by specific examples below.

[0039] Such as figure 1 Shown, the flow chart of the new emotion word extraction method that the present invention provides, step comprises:

[0040] Step 1: Create a product review corpus and preprocess it. Use the word segmentation tool to perform word segmentation, part-of-speech, and location marking for each comment in the corpus, and extract binary word pairs according to the dependency relationship and part-of-speech collocation rules;

[0041] Step 1.1: Use crawlers to crawl product review data from platforms such as Taobao and JD.com to build a product review corpus;

[0042] Step 1.2: Segment each comment in the corpus using spaces, punctuation marks, and stop words, and then normalize the sentences, such as removing special characters, filtering stop words, correcting typos, converting simplified and traditional characters, ...

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 new sentiment word extraction method based on commodity comments, and aims to obtain more new sentiment words in the field of commodity comments. The method specifically comprises the following steps: carrying out preprocessing, word segmentation and part-of-speech and position marking on each comment in a commodity comment corpus, and obtaining (subject words and evaluation words) two-tuples from the comments according to a dependency relationship and a binary collocation extraction rule; carrying out coarse-grained extraction on new sentiment words by adopting features such as part-of-speech and positions of adjacent words, subject words and emoticon positions, and discovering other new sentiment words with a co-location relationship by utilizing a syntax tree;and performing fine-grained screening on the currently extracted new sentiment words through point mutual information value and corpus frequency calculation. According to the new sentiment words extracted by the method, the scale of the sentiment words can be expanded to a certain extent, and a foundation is laid for more comprehensive and accurate sentiment analysis based on commodity comments.

Description

technical field [0001] The invention relates to the technical field of text analysis, in particular to a method for extracting new emotional words based on commodity reviews. Background technique [0002] In the Internet era of information explosion, e-commerce is also gradually changing people's work and life. More and more people are accustomed to online shopping, and major e-commerce platforms have also become the main sales channels for various commodities. In order to better understand the actual evaluation and improve product services, almost all e-commerce websites allow customers to comment on the products they purchase. These reviews include consumers' evaluations and emotional views on each attribute of the product. However, these product review information can not only provide other consumers with objective, comprehensive and true product descriptions, but also promote product research and development and company development, thereby gaining a competitive advanta...

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): G06F40/284G06F40/247G06F40/35
CPCY02D10/00
Inventor 张顺香许汗清尹畅金鸣徐善山孟楠
Owner ANHUI UNIV OF SCI & TECH
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