社会网络视角下民族用户群体行为的识别机制研究
Social Network, Online Public Opinion, Behavior Monitoring, Ethnic Users, Behavioral Analysis

大数据时代，社交网络与人们的生活融合在一起，全民参与网络生活的程度不断提高，社交平台逐步成为政府与公众进行沟通的重要阵地。社交网络的迅速发展，带来了大量的流量与商业价值，同时也吸引了许多通过不正当行为从中渔利的异常用户。如何正确处理网络舆情事件，精准识别异常用户行为，减少其带来的不良影响已成为政府工作的一大重要课题。本文通过研究民族地区网络群体用户异常行为，分析多用户交互行为的特征，利用大数据范式理论与机器学习算法研究相结合的方法，通过网络行为数据进行实时计算，可以实现民族地区热点事件的动态感知，进而对公众行为的发展趋势进行有效地监测。有助于提高社会稳定性，维护社交网络环境，促进民族团结。
In the era of big data, social networks are integrated with people’s lives, the degree of people’s participation in online life is constantly increasing, and social platforms have gradually become an important position for the government to communicate with the public. The rapid development of social networks has brought a lot of traffic and business value, but also attracted many abnormal users who profit from improper behavior. How to correctly deal with online public opinion events, accurately identify abnormal user behavior, and reduce its adverse impact has become a major issue of government work. By studying the abnormal behaviors of network group users in ethnic minority areas, this paper analyzes the characteristics of multi-user interaction behaviors, and uses the method of combining big data paradigm theory and machine learning algorithm research to carry out real-time calculation through network behavior data, which can realize the dynamic perception of hot events in ethnic minority areas, and then effectively monitor the development trend of public behaviors. It helps to improve social stability, maintain the social network environment, and promote national unity.