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

A false comment detection method based on comment external information

A technology for external information and detection methods, applied in the field of service computing, can solve the problem of low detection accuracy, and achieve the effect of ensuring richness and accuracy, good versatility, and improved accuracy

Inactive Publication Date: 2019-04-23
田刚
View PDF16 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the detection accuracy of the existing false comment detection method is not high, the present invention provides a false comment detection method based on the external information of the comment

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 false comment detection method based on comment external information
  • A false comment detection method based on comment external information
  • A false comment detection method based on comment external information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Below is the specific embodiment of the application of the present invention:

[0068] The method is validated using a gold standard dataset. The review data set is collected from a certain website, which contains a total of 5.8 million reviews and 6.7 million products, and based on this data set, 200,000 reviews are randomly selected as the basic data set.

[0069] Execute step 1, first use the seed word "fake" to locate 5 positions in the basic comment data, and then take 500 data in the upper and lower intervals of each position, and obtain a total of 5000 data. These data are highly suspected of being false. Then 5,000 review data are randomly selected from the basic data set, which are less false due to random selection. Then manually classify 10,000 data. The classification standard depends on the text content and attribute of the comment. The attribute of the comment includes the number of useful feedback, the total number of feedback, the rating, the length o...

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 provides a false comment detection method based on comment external information. According to the method, the comment content and the external attribute in the comment document are extracted and labeled; comments and label data sets thereof are formed; comments and tag data sets thereof are divided into a training group and a testing group according to a proportion of 4: 1, and thenperforming the text preprocessing on the training group and the test group, establishing a false comment detection model, extracting an external attribute vector by utilizing a convolutional neural network, extracting a comment content vector by utilizing a long-short-term memory network added with an attention mechanism, and performing linear combination on the extracted features in a linear combination layer after feature extraction. According to the method, the false detection of all international e-commerce English comments can be achieved, good universality is achieved, the precision of the detection method reaches 81.4%, and the detection method can be qualified for most detection tasks.

Description

technical field [0001] The invention relates to the technical field of service computing, in particular to a false comment detection method based on external information of comments. Background technique [0002] With the development of Internet business, in order to allow users to decide their purchase intentions based on their own intentions and the evaluations of other consumers, major e-commerce platforms have developed various user feedback mechanisms, among which the product evaluation system is the most popular one. Since many users tend to read relevant product reviews before making a purchase decision on the e-commerce platform, some criminals use the evaluation system to inject a large number of false reviews on the e-commerce platform to influence the sales of products for the purpose of profit. According to some researchers' statistics, fake reviews account for 14-20% of Yelp sites, and 2-6% of fake reviews in Tripadvisor, Orbitz, Priceline, and Expedia. In this...

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
IPC IPC(8): G06K9/62G06N3/04G06F16/2458
CPCG06N3/045G06F18/24
Inventor 田刚刘鹏飞任艳伟
Owner 田刚
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