OpinionFlow: Visual Analysis of Opinion Diffusion on Social Media

IEEE Transactions on Visualization and Computer Graphics (IEEE VAST 2014)

Yingcai Wu1    Shixia Liu1     Kai Yan*1,2     Mengchen Liu1,3     Fangzhao Wu1,3    
Authors associated with * are/were the interns under the supervision of Yingcai Wu in MSRA
1Microsoft Research Asia       2 Harbin Institute of Technology       3Tsinghua University

Teaser Image
Teaser Image

The interactive user interface of the OpinionFlow system.


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.


Download the paper


OpinionFlow: Visual Analysis of Opinion Diffusion on Social Media from VGTCommunity on Vimeo.

Download the full video (22MB)


@article {YWu2014a,
author = {Yingcai Wu and Shixia Liu and Kai Yan and Mengchen Liu and Fangzhao Wu},
title = {{OpinionFlow}: Visual Analysis of Opinion Diffusion on Social Media},
journal = {IEEE Transactions on Visualization and Computer Graphics (Proceedings of IEEE VAST 2014},
year = {2014},
volume = {20},
number = {12}


The authors would like to thank Furu Wei with Microsoft Research for providing an opinion mining toolkit (SSWE). The authors also thank Prof. Jonathan J.H. Zhu with City University of Hong Kong, and Prof. Tai-Quan Peng with Nanyang Technological University for participating this project as domain experts and providing valuable and constructive suggestion.

Copyright © 2015 by Yingcai Wu. All rights reserved