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

Comment spam recognition method and device

A technology for spam comments and identification methods, applied in the field of spam comment identification methods and spam comment identification devices, can solve problems such as the adverse impact of product impartiality, destroy the true attributes of products and user feedback information, and achieve the integrity and authenticity protection. Effect

Inactive Publication Date: 2017-10-03
ALIBABA GRP HLDG LTD
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Spam comments (especially untrue comments) will have a negative impact on the fairness of the product, destroying the real attributes of the product and user feedback information

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
  • Comment spam recognition method and device
  • Comment spam recognition method and device
  • Comment spam recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Embodiment 1. A method for identifying spam comments.

[0055] figure 1 It is a flow chart of the method for identifying spam comments in this embodiment. Such as figure 1 As shown, the method of this embodiment mainly includes: step S100, step S110 and step S120. The method described in this embodiment is generally executed in a network device, and the method described in this embodiment can be executed in a network device on the side of the online shopping platform.

[0056] next to figure 1 Each step is described in detail.

[0057] S100. Construct a language model for the comment according to the word segmentation in a comment read from the comment collection, so as to obtain the probability of the comment.

[0058] Specifically, the review set in this embodiment includes multiple reviews, and the reviews in the review set are reviews that need to be authenticated as real reviews. The comments in the comment collection in this embodiment usually refer to comme...

Embodiment 2

[0148] Embodiment 2: Spam comment identification device.

[0149] Figure 10 It is a schematic diagram of the device for identifying spam comments in this embodiment. Such as Figure 10 As shown, the device in this embodiment mainly includes: a model building module 1000 , a similarity calculation module 1010 , and an unauthentic judgment module 1020 . In an application scenario, the device of this embodiment may also include: a model building module 1000, a similarity calculation module 1010, an untrue judgment module 1020, a comment acquisition module 1030, and a comment filtering module 1040 (such as Figure 11 shown). The spam comment identification device described in this embodiment is usually set in network equipment. Preferably, the device described in this embodiment is usually set in network equipment on the side of the online shopping platform.

[0150] Combine below Figure 10-Figure 20 The structure of the comment spam identification device of this ...

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 comment spam recognition method and device. The comment spam recognition method includes: constructing a language model for a comment according to a participle of the comment read from a comment set, and acquiring the probability of the comment; calculating the similarity between the two comments according to the probability of the comment and the probability of the other comment in the comment set; and determining that the two comments are untruthful comments when the similarity satisfies a similarity demand. The technical scheme can effectively recognize the untruthful comments, and can protect the integrity and the authenticity of use feedback data.

Description

technical field [0001] The invention relates to Internet technology, in particular to a spam comment identification method and a spam comment identification device. Background technique [0002] In the field of Internet product review technology, spam comments usually include: useless comments and untrue comments, where useless comments mainly refer to random texts without emotional color, comment texts on non-product information, questions and advertisements, etc. The inauthentic comments mainly refer to the intentionally published comments that do not conform to the actual situation based on the promotion of a certain product and the defamation of competitors' products. Inauthentic reviews tend to resemble real reviews more closely than useless ones, and inauthentic reviews tend to be more harmful. [0003] Spam comments (especially untrue comments) will have a negative impact on the fairness of the product, destroying the real attributes of the product and user feedback....

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): G06F17/27
CPCG06F40/279G06F40/30
Inventor 刘立佳
Owner ALIBABA GRP HLDG 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