

Social bots, as a computer program, can control social accounts, automatically post tweets on social platforms and use relevant technologies such as artificial intelligence to mimic and interact with human users 10. Therefore, it is of great significance to dilute harmful information spreading and guide public opinion in a positive way when a major emergency occurs 8.Īccording to the research report of Oxford Internet Institute 9, the influence of the social bots on mainstream OSNs in the United States, Russia, Germany, Canada, China and other countries can not be underestimated. This would cause adverse effects on enterprises, institutions and even government departments. They usually deliberately interpret or comment on certain events maliciously, guiding and inciting the negative emotions of other users. However, due to its openness and freedom, some irrational users or spammers will release various kinds of harmful information such as rumor 3, 4, hate speech 5, 6 and fake news 7 on the platform. It has become an important channel for the masses to obtain information and express their views and attitudes on current hot issues. As one of the most popular online social media, Sina Microblog had 486 million active users in June 2019 and average daily users of 211 million 2. It is reported that, by April 2019, Global Internet users grew by 8.6% over the past twelve months, with almost 3.5 billion people using social media 1. The Internet has become the main way for people to release and obtain information. With development of information technology and the popularity of the Internet, more and more people express their personal views and opinions through the Internet. The study in this paper sounds an alarm for Sina Microblog defense mechanism and provides a valuable reference for social bots detection. The results show that the infiltration strategies we proposed are effective and can help social bots escape detection of Sina Microblog defense mechanism as well. Finally, our social bots gained 5546 followers in the 42-day infiltration period with a 100% survival rate.

Then, we constructed 96 social bots in Sina Microblog and researched the influence of different infiltration strategies, like different attribute settings and various types of interactions.

Firstly, we studied the critical technology of Sina Microblog data collection, which indicates that the defense mechanism of that is vulnerable. In this paper, we studied the automated construction technology and infiltration strategies of social bots in Sina Microblog, aiming at building friendly and influential social bots to resist malicious interpretations. What is more, the existence of social bots is so powerful that some of them can turn into influential users. The widespread use of these OSNs has also led to the emergence of social bots. Nowadays, millions of people use Online Social Networks (OSNs) like Twitter, Facebook and Sina Microblog, to express opinions on current events.
