Emergent local structures in an ecosystem of social bots and humans on Twitter
Emergent local structures in an ecosystem of social bots and humans on Twitter
复制标题
DOI：
10.1140/epjds/s13688-023-00406-5
复制
发表时间：
2023-09-22
期刊：
影响因子：
3.6
通讯作者：
Kertesz，Janos
中科院分区：
文献类型：
--
作者：
Alrhmoun，Abdullah;Kertesz，Janos
在线社交网络中的机器人可以被用于好的或坏的目的，但它们的存在是不可避免的，并且在未来会增加。为了研究机器人和人类的交互网络如何演变，我们在Twitter上创建了六个带有AI语言模型的社交机器人，并让它们执行标准的用户操作。机器人实施了三种不同的策略：趋势定位策略（TTS），关键词定位策略（KTS）和用户定位策略（UTS）。我们研究了交互模式，如定位用户，传播信息，传播关系和参与。我们专注于新兴的本地结构或图案，并发现社交机器人的策略对它们产生了重大影响。在TTS或KTS之后与机器人交互产生的图案很简单，并且显示出显著的重叠，而与UTS控制的机器人交互产生的图案则更复杂。这些发现为在线社交网络中的人机交互模式提供了深入见解，并可用于开发更有效的机器人以执行有益任务并打击恶意行为者。
Bots in online social networks can be used for good or bad but their presence is unavoidable and will increase in the future. To investigate how the interaction networks of bots and humans evolve, we created six social bots on Twitter with AI language models and let them carry out standard user operations. Three different strategies were implemented for the bots: a trend-targeting strategy (TTS), a keywords-targeting strategy (KTS) and a user-targeting strategy (UTS). We examined the interaction patterns such as targeting users, spreading messages, propagating relationships, and engagement. We focused on the emergent local structures or motifs and found that the strategies of the social bots had a significant impact on them. Motifs resulting from interactions with bots following TTS or KTS are simple and show significant overlap, while those resulting from interactions with UTS-governed bots lead to more complex motifs. These findings provide insights into human-bot interaction patterns in online social networks, and can be used to develop more effective bots for beneficial tasks and to combat malicious actors.