A Method for Identifying Chinese False Customer Reviews

A recognition method and fake technology, applied in the field of recognition of Chinese fake customer reviews, can solve the problem of low recognition rate and achieve the effect of improving the recognition rate

Active Publication Date: 2017-09-29
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for identifying false customer reviews in Chinese, which overcomes the problem of low recognition rate in the prior art, so as to quickly and accurately identify false customer reviews on domestic e-commerce websites

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
  • A Method for Identifying Chinese False Customer Reviews
  • A Method for Identifying Chinese False Customer Reviews
  • A Method for Identifying Chinese False Customer Reviews

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0074] Example 2: Large sample calculation example:

[0075] Calculate the 4,000 comments of a Huawei mobile phone, get the word frequency statistics and sentiment score of each comment, and calculate its word frequency outlier and emotional outlier as two features. The third feature is whether to use template comments, that is, whether there are comments with the same part-of-speech sentence structure. If there is, this feature is 1, and if not, it is 0. The fourth feature is the number of times a comment is repeatedly posted by the same user.

[0076] At the same time, the information of users of each sentence pattern template and the information of users of 150 invalid comments (without valid collocation) were collected.

[0077] The inventor thinks that group comments often use the same template with each other, and make multiple comments on the product. If in different product reviews, compare the number of times the template comment publisher and the user have posted co...

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 relates to a method for identifying false Chinese customer reviews, comprising the following steps: a) reading in review data one by one; b) segmenting the reviews into words to obtain the part-of-speech sequence, grammatical components and structural features of the sentences; c) at least dividing them into the following two Partially perform feature extraction on a comment at the same time: word number distribution outlier feature extraction, emotion distribution outlier feature extraction; according to the extracted results, comments whose outlier value exceeds the set threshold are marked as false comments. The invention has the following advantages: adding sentiment analysis of customer comment content, well identifying invalid comments and irrelevant comments, calculating the emotional outlier degree of comments, and improving the recognition rate of Chinese false comments.

Description

technical field [0001] The invention relates to a method for identifying false customer comments in Chinese, which can quickly and accurately identify false customer comments on domestic e-commerce websites. technical background [0002] With the rapid development of e-commerce, the automatic identification of false customer reviews is becoming more and more important. Customer reviews are a key part of solving the mutual trust between the two parties in online transactions and making up for the lack of physical experience of products. It can be said that the value of integrity is more prominent in online transactions. But if the reviews themselves are false, the foundation of the transaction will be affected; if such false reviews are allowed to proliferate, then it will damage not only the two parties in the transaction, but the entire e-commerce industry. [0003] But there is no automatic identification system for Chinese fake customer reviews applied to e-commerce plat...

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): G06F17/27G06F17/30
Inventor 李秀闫欣伟杜佳陈胜
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
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