网络与信息安全学报 (Jun 2024)
Analysis method on the properties of social networks of internet nuisance communities
Abstract
With the widespread adoption of the Internet and an increase in the number of Internet users, the security of the network environment has been seriously threatened by Internet public hazards organizations, such as the Internet water army and the internet public hazards community. Given the characteristics of these organizations, which include being distant from domestic supervision and possessing strong concealment and camouflage abilities, a social network characteristic analysis method was proposed for Internet public hazards organizations. Initially, at the user characteristic level, the influence distribution of group members was calculated through centrality measurement to identify the core users with the greatest influence, and an analysis of the anonymity characteristics of these core members was conducted. Subsequently, at the complex network characteristic level, the cluster status and resource distribution within the community were studied through the analysis of small-world effects and scale-free characteristics. Finally, at the temporal characteristic level, after preprocessing the post content of core members, BERTopic was utilized for dynamic topic modeling to ascertain the relationship between community themes and time. A large number of experimental performance analyses have verified the effectiveness of the proposed method. The research results can be utilized to analyze the characteristics of public hazard communities, track criminal activity trajectories, and provide theoretical references for the investigation and crackdown of public hazard organizations, as well as for the design of automated detection systems.
