Exploring the construction and infiltration strategies of social bots in sina microblog

Abstract

Nowadays, millions of people use Online Social Networks (OSNs) like Twitter, Facebook and Sina Microblog, to express opinions on current events. The widespread use of these OSNs has also led to the emergence of social bots. What is more, the existence of social bots is so powerful that some of them can turn into influential users. 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. Firstly, we studied the critical technology of Sina Microblog data collection, which indicates that the defense mechanism of that is vulnerable. 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. Finally, our social bots gained 5546 followers in the 42-day infiltration period with a 100% survival rate. 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. The study in this paper sounds an alarm for Sina Microblog defense mechanism and provides a valuable reference for social bots detection.

Influence of social bots in information warfare: A case study on @UAWeapons Twitter account in the context of Russia–Ukraine conflict

“…Shen et al (2023) conducted a similar study by collecting 3,816 random bot accounts related to the Russian–Ukrainian conflict from 17 February to 17 March 2022 and concluded that the average number of bot account followers was 988, and the median number was 174. In another study, 96 bots were deployed on a social platform and gained 5,546 followers in total over the course of 42 days (Wang et al, 2020). As such, @UAWeapon stands out from similar ones due to its rapid growth in followers within a relatively short period of time, and therefore, it was selected as the subject of this study.…”

SEGCN: a subgraph encoding based graph convolutional network model for social bot detection

“…The group-based social bot detection method utilizes the structural differences between the social graphs generated by humans and bots. The relationships that are used to build the social graph are usually friend relationships 33 , following/follower 34 , 35 , retweet/retweeted 36 . The detection mechanism is to use the homogeneity of social networks, in another word, the neighbor nodes of the bot tend to be bots, and the neighbor nodes of the human tend to be humans 34 , 37 – 39 .…”

Research on Work Strategies and Workflow of Social Bots

“…After creating accounts, the controllers may use network crawlers and machine learning to build up the interaction and feedback capabilities of social bots when communicating with human users. According to Wang et al [8], the controllers use network crawlers to collect four types of information about human users: social network information, profile information, posts, and comments. The information gathered by a network crawler would be saved in a database.…”

“…This process can help social bots confirm the object of an interaction. According to related studies, at this stage, social bots may retweet content to users with the same stance, and bots may also intentionally retweet content to users with opposite stances to trigger an opinion conflict, which may draw more attention from human users [8].…”