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

Spam comment detection method and device

A technology for spam comments and detection methods, applied in image data processing, special data processing applications, instruments, etc., can solve the problems of the authoritativeness of commenters are not always reliable, and the detection accuracy of spam comments is low, and achieve the effect of high detection accuracy.

Inactive Publication Date: 2015-11-25
RICOH KK
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, according to this technique, it takes a lot of time to manually label data such as a reviewer's previous comments; and the authoritativeness of a reviewer determined by, for example, establishing a probabilistic model is not always reliable, leading to the detection of comment spam low precision

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 method and device
  • Spam comment detection method and device
  • Spam comment detection method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0022] figure 2 A flowchart showing a method for detecting comment spam of an image capture device according to the first embodiment of the present invention.

[0023] Such as figure 2 As shown, in step S201, feature words and emotion words in a comment are extracted, and the first emotion polarity of the emotion words is determined.

[0024] Emotional words are words expressing emotions, which can be nouns, verbs, adjectives, interjections and some fixed terms. Sentiment polarity reflects a tendency of sentiment and may include, for example, positive sentiment, neutral sentiment, and negative sentiment. Sentiment words and sentiment polarity are commonly used terms in this field, and will not be introduced in detail here.

[0025] Basic comments containing a single point of view can be written with a quintuple O i =(e j ,a k ,s l ,h m ,t n ) to represent, where O i is the commenter h m at time t n Published, for the target object / entity e j the a k Features / As...

no. 2 example

[0043] In the method for detecting spam comments of an image capture device according to the first embodiment of the present invention, for a comment whose first emotional polarity is consistent with the second emotional polarity, it is defaulted to be an objective comment, that is, not a spam comment. However, in fact, when the first emotional polarity is consistent with the second emotional polarity, the comments on the image capture device are not necessarily objective. For example, even if a negative review about a camera is negative and the image features are of poor quality (i.e., when the first and second sentiment polarities are both negative), the negative review cannot be deemed to be Objectively, since the poor quality of image features may be caused by improper parameter settings when using the camera to capture the image, the camera should not be considered bad at this time.

[0044] specific, Figure 5 A possible correspondence between the first emotional polari...

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 present invention provides a detection method and a detection device for a spam comment of an image capture device. The detection method comprises: extracting a feature word and a sentiment word in a comment, and determining a first sentiment polarity of the sentiment word; determining a second sentiment polarity of an image feature corresponding to the feature word and the sentiment word in a related image shot by the image capture device; and comparing the first sentiment polarity with the second sentiment polarity, and if the first sentiment polarity is not consistent with the second sentiment polarity, determining that the comment is the spam comment. According to the method, objectivity of the comment is evaluated based on specific factors such as comment information and the related image, so that the method has higher detection accuracy; and the method does not need a large amount of labor time for processing, so that the spam comment can be rapidly detected.

Description

technical field [0001] The present invention generally relates to network information processing, and specifically relates to a method and device for detecting spam comments of an image capture device. Background technique [0002] In recent years, with the development of the Internet, people are more and more fond of expressing their opinions on the Internet. For example, users can post comments on commodities on major commercial websites, forums, and blogs when purchasing commodities. These review information are very important to the product provider, which can help the product provider understand the shortcomings or deficiencies of the product, and then be used to improve the next generation of products. On the other hand, these review information are also very important to other users, which can help other users to quickly understand the performance, advantages and disadvantages of the product, so that they can make better purchase decisions and choices when selecting ...

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): G06F17/27G06T7/00
Inventor 郑继川白瑞峰姜珊珊
Owner RICOH KK