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

Spam comment detection and classification system and method under cold start condition

A spam comment and classification method technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of inapplicability, low accuracy of spam comment detection, unsatisfactory effect of text semantic understanding method, etc., and achieve classification Accurate and accurate, the effect of a wide range of application scenarios

Inactive Publication Date: 2021-02-05
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the accuracy of spam comment detection based on linguistic features is usually not high; spam comment detection based on behavioral features requires long-term observation and a large amount of data support, and is not suitable for data-scarce situations such as the cold start problem.
Therefore, the effect of the text semantic understanding method in the related art is not ideal in the case of cold start

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
  • Spam comment detection and classification system and method under cold start condition
  • Spam comment detection and classification system and method under cold start condition
  • Spam comment detection and classification system and method under cold start condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Such as figure 1 as shown, figure 1 It is a schematic structural diagram of the spam comment detection and classification system in the cold start situation of the present invention, including:

[0033] The easy-to-get information generation module is used to generate easy-to-get information for new users and old users;

[0034] The real behavior characteristic feature extraction module is used to extract the real behavior characteristics of old users from a large amount of data of old users;

[0035] Generative adversarial network module is used to use the real behavior characteristics of old users as the real data of the generated adversarial network discriminator, and train the generated adversarial network by using the easy-to-obtain information of old users as the generator's constraints;

[0036] The feature generation module is used to generate the behavioral features of new users by using the generated confrontation network generator trained on the old user da...

Embodiment 2

[0040] Such as figure 2 , image 3 As shown, a spam comment detection and classification method under cold start conditions is provided, which specifically includes the following steps:

[0041] Step s1: For old users, pre-process easily obtained information;

[0042] Step s2: For old users, generate behavioral characteristics of old users through old user comment information collected for a long time;

[0043] Step s3: For the old users, use the behavioral characteristics of the old users as the real data of the discriminator of the generated adversarial network, and use the readily available information of the old users as the constraints of the generator to train the generated adversarial network;

[0044] Step s4: For new users, repeat step s1;

[0045] Step s5: put all the easy-to-obtain information of the new user into the generator obtained from the old user data in step s3, and generate the behavior characteristics of the new user;

[0046] Step s6: Using the meth...

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 spam comment detection and classification system and method under a cold start condition, and the method comprises the steps: training a generative adversarial network through employing the behavior characteristics and easy-to-obtain information of an old user with a large amount of data; and then generating behavior characteristics of the new user by using the trained generator by using the readily available information of the new user, and finally classifying the users according to the generated behavior characteristics subjected to domain self-adaption. The methodsupports junk comment classification, junk comment detection can be carried out under the condition that available data is very deficient and cold start is carried out, and a good effect is achieved.

Description

technical field [0001] The invention relates to the technical field of data analysis, in particular to a spam comment detection and classification system and method under cold start conditions. Background technique [0002] With the development of artificial intelligence, the use of artificial intelligence technology for data analysis has become an important application direction. Especially in recent years, with the rapid development of mobile Internet technology, online review sites have a large number of comments, and these comments may be spam comments. In related technologies, the mainstream method is based on language features and behavior features. Spam comment detection. However, the accuracy of spam comment detection based on linguistic features is usually not high; spam comment detection based on behavioral features requires long-term observation and a large amount of data support, and is not suitable for data-scarce situations such as the cold start problem. Ther...

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): G06K9/62
CPCG06F18/24G06F18/214
Inventor 司成良展华益王欣骆敏蒋伟
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
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