Exploring the collective human behavior in cascading systems: a comprehensive framework
- PDF / 2,612,399 Bytes
- 25 Pages / 439.37 x 666.142 pts Page_size
- 89 Downloads / 148 Views
Exploring the collective human behavior in cascading systems: a comprehensive framework Yunfei Lu1 · Linyun Yu1 · Tianyang Zhang1 · Chengxi Zang1 · Peng Cui1 · Chaoming Song2 · Wenwu Zhu1 Received: 4 January 2019 / Revised: 3 August 2020 / Accepted: 9 August 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract The collective behavior describing spontaneously emerging social processes and events is ubiquitous in both physical society and online social media. The knowledge of collective behavior is critical in understanding and predicting social movements, fads, riots, and so on. However, detecting, quantifying, and modeling the collective behavior in cascading systems at large scale are seldom explored. In this paper, we examine a real-world online social media with more than 1.7 million information spreading records. We observe evident collective behavior in information cascading systems and then propose metrics to quantify the collectivity. We find that previous information cascading models cannot capture the collective behavior in the real-world data and thus never utilize it. Furthermore, we propose a comprehensive generative framework with a latent user interest layer to capture the collective behavior. Our framework accurately models the information cascades with respect to dynamics, popularity, structure, and collectivity. By leveraging the knowledge behind collective behavior, our model successfully predicts the popularity and participants of information cascades without temporal features or early stage information. Our framework may serve as a more generalized one in modeling cascading systems, and, together with empirical discovery and applications, advance our understanding of human behavior. Keywords Collective human behavior · Information cascades · Generative framework · Point process
1 Introduction Collective behavior describes the phenomenon that people exhibit the same behavior in a spontaneous way which does not reflect the existing social structure [28]. The collective behavior lies in various social phenomena, ranging from the worldwide stock crashes in ¨ 2018, the popularity of the billion-view-video Gangnam Style, to inconspicuous ones such
B
Yunfei Lu [email protected]
1
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
2
Department of Physics, University of Miami, Coral Gables, FL, USA
123
Y. Lu et al.
as several customers having meals in a restaurant at some point. The collective behavior underlying these phenomena cannot be explained by existing social structure but indicates that they share some unknown common points, which may be social-economic factors, interests, or eating habits. Although there are different opinions on interpretations, the existence and significance of collective behavior are widely recognized by the public. The usefulness of the understanding of collective behavior is further proven by different research topics, such as predicting human mobility [3] and analyzing human activity patter
Data Loading...