Unlock instant, AI-driven research and patent intelligence for your innovation.

User comment viewpoint extraction and viewpoint tag generation method

A technology of user comments and opinions, applied in data processing applications, character and pattern recognition, special data processing applications, etc., can solve problems such as non-similarity and uncontrollable clustering scale, achieve accurate comment labels, improve recall rate, The effect of good applicability

Inactive Publication Date: 2018-08-03
ZHEJIANG UNIV
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods are sensitive to the initial value, that is, the scale of clustering cannot be controlled, and the commonality under the same category may not be semantic similarity
At the same time, it is not suitable to use the same label for product reviews of different categories and polarities

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
  • User comment viewpoint extraction and viewpoint tag generation method
  • User comment viewpoint extraction and viewpoint tag generation method
  • User comment viewpoint extraction and viewpoint tag generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments, and the object and effect of the present invention will become more apparent.

[0043] figure 1 A flow chart of the method of the present invention is given. The present invention performs opinion extraction and opinion label generation on user comments into two steps, namely, firstly performs opinion extraction on user comments, and then aggregates the extracted opinions to generate opinion labels.

[0044] The present invention to extract opinions from user comments refers to extracting opinions from a specific comment of a specific product. Generating opinion labels for user comments refers to generating several general opinion labels by synthesizing the evaluations of multiple users on the product.

[0045] like figure 1 As shown, in step 101, the specific steps for extracting opinions from user comments are as follows:

[0046] (1.1...

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 user comment viewpoint extraction and viewpoint tag generation method. The method comprises the steps of firstly establishing an initial viewpoint part-of-speech rule librarybased on user comments, then automatically discovering new user viewpoint part-of-speech rules through a continuous iteration method, and obtaining user comment viewpoints through a part-of-speech rule matching method; and for the extracted viewpoints, generating an attribute word bank of commodities from top to bottom based on a category tree structure, and performing collection according to viewpoint polarity to generate user comment viewpoint tags of the commodities. Through the method for automatically discovering the comment viewpoint part-of-speech rules, the recall rate of user viewpoint extraction is increased; and hierarchical clustering and polarity analysis of words improve the accuracy of viewpoint clustering, so that the obtained user comment viewpoint tags are more comprehensive and accurate.

Description

technical field [0001] The invention relates to a method for extracting opinions from user comments and generating opinion labels. Specifically, it relates to a method of extracting user comments and opinions from the comments when a user comment of a certain product is given, and then aggregating the user comments and opinions to generate user comment and opinion labels. Background technique [0002] User reviews are the user's evaluation of the product, and it is the communication method between the user and the product provider, which reflects the user's preference and demand for the product. The commodity here is a generalized commodity concept, in addition to tangible products, it can also be intangible software and services. Product review tags can not only save users’ time for reviewing reviews, but also allow product providers to get user feedback faster. Therefore, automatically extracting user opinions from user reviews of products and automatically generating 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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06K9/62G06Q30/06
CPCG06F16/353G06Q30/0625G06F18/23213
Inventor 纪志伟杜歆
Owner ZHEJIANG UNIV