Social robot identification method based on graph attention network

A technology of attention and robotics, applied in instruments, special data processing applications, electronic digital data processing, etc., can solve problems such as bad content, reduce opportunities to take advantage of, weaken the influence of bad public opinion, and maintain social harmony and stability Effect

Active Publication Date: 2020-06-12
HANGZHOU DIANZI UNIV
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In recent years, with the development of social networks, individuals can fully express their voices on the Internet, but it also gives criminals an opportunity to publish bad content on the Internet.

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
  • Social robot identification method based on graph attention network
  • Social robot identification method based on graph attention network
  • Social robot identification method based on graph attention network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Such as figure 1 As shown, the social robot identification method of the present invention, the steps are as follows:

[0034] Step (1), collect a certain piece of content posted by some users on Weibo within one day and the mutual comment relationship, and the number of accounts is about 3000. Record the content posted by an account on the social platform, and collect the substantive comment content and comments posted by the comment account under the content at the same time. At the same time, judge whether the account is a robot based on the content posted by the account and the comment relationship.

[0035] figure 2 It is a schematic diagram of the social network in the present invention.

[0036] Step (2), performing natural language processing on the substantive content published by all collected accounts to obtain a data set. Firstly, high-frequency words such as "de" and "yes" are removed. Then select about 1500 commonly used words and arrange them in a c...

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 social robot identification method based on a graph attention network. The method is based on a graph attention network, natural language processing is carried out on contentpublished on a social network to construct node features and forwarding and comment relations among social accounts to construct a graph, then classification is carried out, and therefore whether theaccounts are social robots or not is judged. The method comprises the following steps: firstly, creating a data set by social network data, then constructing a graph attention network, and training and testing the graph attention network through the created data set. Aiming at the complex social network robot identification problem, the method can automatically and efficiently identify the socialrobot and reduce the opportunities of lawbreakers, thereby limiting the speech published by the robot, weakening the influence of bad social public opinions, and being beneficial to maintaining the harmony and stability of the society.

Description

technical field [0001] The present invention relates to the application field of the graph attention network, in particular to the node classification technology based on the graph attention network and its actual application to the field of social networks. Background technique [0002] In recent years, with the development of social networks, individuals can fully express their voices on the Internet, but it also gives criminals an opportunity to publish bad content on the Internet. Especially on Weibo, which is full of trolls and zombie fans, social robots can publish a large amount of content to influence the direction of public opinion. Therefore, a system is needed to identify social robots and control the social impact of the speeches released by robots. [0003] In computer science, a graph is a data structure consisting of vertices and edges. A graph G can be described by a set of vertices V and the edges E it contains, namely: [0004] G=(V,E) (1) [0005] Verti...

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): G06F16/9536
CPCG06F16/9536
Inventor 颜成钢阮定孙垚棋张继勇张勇东
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap