Social robot detection method and system capable of blending user behaviors with text information

Abstract

The invention belongs to the technical field of computers, particularly provides a social robot detection method and system capable of blending user behaviors with text information, and aims to solvethe problem in the prior art that characteristics are manually selected, logicality and a time sequence between social media posts are ignored and the user behavior information of a social platform isignored. The social robot detection method comprises the following steps that: obtaining the historical network data and the friend network data of a social media user to be detected; on the basis ofthe above data, obtaining a user text characteristic vector, a behavior characteristic vector and a friend network characteristic network, and blending all vectors to obtain the user characteristic vector of the social media user to be detected; and detecting the user characteristic vector to output a detection result. The method disclosed by the invention more conforms to the own characteristicsof the social media, the social media user to be detected is analyzed from multiple dimensions, and detection accuracy is improved. The system also has the above beneficial effects.

Description

technical field [0001] The invention belongs to the field of computer technology, and in particular relates to a method and system for detecting social robots that integrate user behavior and text information. Background technique [0002] With the rapid development of Internet technology and social media platforms, there are a large number of social robots on major social media platforms at home and abroad. These social robots create and publish false news, spread rumors, create network traps, and influence or even manipulate the development trend of public opinion. , these behaviors seriously interfere with the normal life of netizens, threaten the privacy and security of social media users, and even have a bad impact on society. Therefore, how to accurately detect robots in social media platforms and prevent social robots from bringing It has very important practical value. [0003] The early identification of social robots mainly relied on specific artificial strategies...

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of Internet technology and social media platforms, there are a large number of social robots on major social media platforms at home and abroad. These social robots create and publish false news, spread rumors, create network traps, and influence or even manipulate the development trend of public opinion. , these behaviors seriously interfere with the normal life of netizens, threaten the privacy and security of social media users, and even have a bad impact on society. Therefore, how to accurately detect robots in social media platforms and prevent social robots from bringing negative impact, has very important practical value

[0003] The early identification of social robots mainly relied on specific artificial strategies, starting from the fact that social robots increase their influence by making friends extensively, and randomly created a large number of detection seed accounts. These accounts have no actual behavior and will not publish meaningful content. , so human users will not establish friendly relationships with them, and finally detect social robots from accounts that have established friendly relationships with seed accounts through a series of rules, but this method is primitive and simple, and requires more manpower and time, so it cannot be well Then, a social robot analysis method based on network structure analysis was proposed. This method assumes that spam accounts will only be connected to a small number of real users, and most of the rest are spam accounts. This feature is used to identify dense connections. For the text information of social media, a related method based on language features is proposed. This method analyzes the average length of the published text information by analyzing specific vocabulary and punctuation marks, and statistics the URL (Uniform Resoure Locator, unified resource locator), the average length of

[0004] The existing social robot detection methods mainly have the following problems: 1. Based on the existing statistical methods and machine learning methods, it is necessary to manually select features, which consumes a lot of labor costs; 2. The existing social robot detection methods will The content is treated as plain text information, ignoring the logic and timing between social media posts; 3. The methods in the prior art often ignore the behavior information of users in social platforms, or only use simple statistical methods to analyze, which cannot be effective Analyzing and utilizing user behavior information in social platforms

Images