Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Product-oriented sentiment analysis method and system based on fuzzy ontology

A product and aspect technology, applied in the field of product-oriented sentiment analysis method and system based on fuzzy ontology

Active Publication Date: 2017-11-21
刘耀强
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is currently no research work on automatic ontology learning methods for product-oriented sentiment analysis.

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
  • Product-oriented sentiment analysis method and system based on fuzzy ontology
  • Product-oriented sentiment analysis method and system based on fuzzy ontology
  • Product-oriented sentiment analysis method and system based on fuzzy ontology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0095] The primary purpose of the present invention is achieved through the following technical solutions: based on fuzzy ontology-oriented product sentiment analysis and product recommendation methods, including:

[0096] The construction of product fuzzy ontology is based on fuzzy sets and fuzzy relations to describe the uncertainty of product aspect recognition and context-sensitive emotional prediction;

[0097] Product aspect mining based on the latent topic model, applying the probabilistic generation model, extracting product aspects from the corpus D that contains product descriptions and consumer reviews, and obtaining the inclusion relationship between aspects through the probabilistic language model to generate product fuzzy ontology Aspect classification relationships in

[0098] Context-dependent sentiment learning in product ontology, by learning offline from a set of consumer reviews including user ratings to establish non-categorical relationships between senti...

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 product-oriented sentiment analysis method and system based on fuzzy ontology, the method comprising: product fuzzy ontology, product aspect mining based on latent topic model, context-related sentiment learning in product ontology, and product-oriented sentiment Analysis and product recommendation; the system includes: query processor module, social comment retrieval module, social comment crawling module, text preprocessor module, product ontology mining module, product-oriented sentiment analysis module and product-oriented product recommendation module . The present invention can extract various aspects of commodities with definite descriptions and clear distinctions between aspects; in addition, the present invention can make full use of a large number of consumer comments on social media sites to extract fine-grained market feedback information, thereby helping enterprises to apply The social analysis method disclosed in the present invention captures the collective social intelligence in the network to improve their product design and marketing strategy.

Description

technical field [0001] The invention relates to the research field of product sentiment analysis, in particular to a product-oriented sentiment analysis method and system based on fuzzy ontology. Background technique [0002] In the era of Web 2.0, a large amount of data contributed by users (for example, consumer reviews on products) is published to various social media (for example, epinions.com and facebook.com) and e-commerce websites (for example, amazon.com )superior. However, the problem of information overload makes it extremely difficult for businesses or individual consumers to capture the social intelligence embedded in these online reviews. The explosion of user-provided data (eg, consumer reviews) in social networks has driven the development of social analysis tools to automatically extract, analyze, and summarize user-generated content. Among them, sentiment analysis (also known as opinion mining, opinion analysis, or subjectivity analysis) is an important s...

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 Patents(China)
IPC IPC(8): G06Q30/02
Inventor 刘耀强
Owner 刘耀强
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
Eureka Blog
Learn More
PatSnap group products