Blowing Seeds Across Gardens: Visualizing Implicit Propagation of Cross-Platform Social Media Posts
Jianing Yin - Zhejiang University, Hangzhou, China
Hanze Jia - Zhejiang University, Hangzhou, China
Buwei Zhou - Zhejiang University, Hangzhou, China
Tan Tang - Zhejiang University, Hangzhou, China
Lu Ying - Zhejiang University, Hangzhou, China
Shuainan Ye - Zhejiang University, Hangzhou, China
Tai-Quan Peng - Michigan State University, East Lansing, United States
Yingcai Wu - Zhejiang University, Hangzhou, China
Download camera-ready PDF
Room: Bayshore III
2024-10-17T18:33:00ZGMT-0600Change your timezone on the schedule page
2024-10-17T18:33:00Z
Fast forward
Keywords
Propagation analysis, social media visualization, cross-platform propagation, metaphor design
Abstract
Propagation analysis refers to studying how information spreads on social media, a pivotal endeavor for understanding social sentiment and public opinions. Numerous studies contribute to visualizing information spread, but few have considered the implicit and complex diffusion patterns among multiple platforms. To bridge the gap, we summarize cross-platform diffusion patterns with experts and identify significant factors that dissect the mechanisms of cross-platform information spread. Based on that, we propose an information diffusion model that estimates the likelihood of a topic/post spreading among different social media platforms. Moreover, we propose a novel visual metaphor that encapsulates cross-platform propagation in a manner analogous to the spread of seeds across gardens. Specifically, we visualize platforms, posts, implicit cross-platform routes, and salient instances as elements of a virtual ecosystem — gardens, flowers, winds, and seeds, respectively. We further develop a visual analytic system, namely BloomWind, that enables users to quickly identify the cross-platform diffusion patterns and investigate the relevant social media posts. Ultimately, we demonstrate the usage of BloomWind through two case studies and validate its effectiveness using expert interviews.