OpinionFlow: Visual Analysis of Opinion Diffusion on Social Media

• Published in: IEEE transactions on visualization and computer graphics Vol. 20; no. 12; pp. 1763 - 1772
• Main Authors: Wu, Yingcai, Liu, Shixia, Yan, Kai, Liu, Mengchen, Wu, Fangzhao
• Format: Journal Article
• Language: English
• Published: United States IEEE 31.12.2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Communication; Computer Graphics; Data visualization; Humans; Informatics - methods; Information analysis; Media; Propagation; Public Opinion; Social Media; Social network services; Social networks; Twitter; Visual analytics; level-of-detail; kernel density estimation; influence estimation; Opinion visualization; opinion diffusion; opinion flow
• ISSN: 1077-2626; 1941-0506
• DOI: 10.1109/TVCG.2014.2346920

It is important for many different applications such as government and business intelligence to analyze and explore the diffusion of public opinions on social media. However, the rapid propagation and great diversity of public opinions on social media pose great challenges to effective analysis of opinion diffusion. In this paper, we introduce a visual analysis system called OpinionFlow to empower analysts to detect opinion propagation patterns and glean insights. Inspired by the information diffusion model and the theory of selective exposure, we develop an opinion diffusion model to approximate opinion propagation among Twitter users. Accordingly, we design an opinion flow visualization that combines a Sankey graph with a tailored density map in one view to visually convey diffusion of opinions among many users. A stacked tree is used to allow analysts to select topics of interest at different levels. The stacked tree is synchronized with the opinion flow visualization to help users examine and compare diffusion patterns across topics. Experiments and case studies on Twitter data demonstrate the effectiveness and usability of OpinionFlow.