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

A cross-modal detection method for network water army

A cross-modal and network-based technology, applied in network data retrieval, network data indexing, and other database retrieval, etc., can solve the problems of non-correspondence between pictures and products and low similarity of pictures

Inactive Publication Date: 2019-01-18
BEIJING JIAOTONG UNIV
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In another situation, many sailors do not buy products, and merchants do not deliver goods, so sailors upload pictures casually, so that the pictures in the comments do not correspond to the products
The text reviews are similar, but the pictures in the reviews have nothing to do with the actual product, so the picture similarity will be extremely low

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 cross-modal detection method for network water army
  • A cross-modal detection method for network water army
  • A cross-modal detection method for network water army

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0099] In this example, the comments of Taobao, which is the most widely used in my country, are selected as the research object. Through questionnaire survey combined with daily life experience, it can be found that many false comments will be encountered in the process of daily shopping on Taobao, and there are also fake comments on Taobao. A large amount of valuable user review data. In order to be close to real reviews, many trolls will publish product pictures while posting text reviews, and buyers usually directly select reviews with pictures to view. Therefore, by analyzing the characteristics of troll behavior and comments, a cross-modal detection method for cyber trolls is proposed. figure 1 An overall algorithm flow diagram of a method for cross-modal detection of network trolls provided by an embodiment of the present invention; figure 1 Shown:

[0100] According to the data requirements of the detection algorithm in this paper, the web crawler is implemented by pr...

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 method for cross-modal detection of network water army. The method comprises the following steps: firstly, obtaining web page comment data, preprocessing the comment data to obtain reduced data; then, extracting text features and image features of the reduced data, and converting the extracted text features and image features into text and image feature vectors; finally, the text and image feature vector dataset is used for cross-modal learning, and the network water army information is obtained. The invention combines and converts the text and the picture by using thecross-modal method, endows the picture with the corresponding classified text label through training and machine learning, converts the similarity of the picture comment into the similarity of the text comment, and quickly and accurately detects the water army in the network comment through the algorithm.

Description

technical field [0001] The invention relates to the technical field of network troll detection, in particular to a method for cross-modal detection of cyber trolls. Background technique [0002] In the Internet age, a large number of comments in social platforms, e-commerce, news websites and other fields play a very important role. However, there are a large number of tendentious false comments published by online trolls in these comments, which will affect users' views and guide public opinion. In recent years, online shopping has become a part of people's life. Although consumers enjoy the convenience brought by online shopping, due to the virtual nature of the Internet, it is difficult for consumers to choose among dazzling products only through pictures provided by merchants. Best item of great quality. Therefore, consumers often refer to the reviews in the products to make decisions, but in order to improve reputation, sales, and baby popularity, most merchants use t...

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): G06F16/951G06F16/9538G06F16/33G06F16/50G06F16/58
Inventor 白肖璇相迎宵陈彤王盈地刘京京窦帅代磊陈一昊牛温佳刘吉强
Owner BEIJING JIAOTONG UNIV
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