PKUVIS Weibo Visual Analytics

We propose novel visual analysis techniques to solve different problems in social media, including the diffusion of messages, event evolution, sentiment analysis, geographical movements.


WeiboEvent is a visual analytic system for analyzing events of Weibo, a Chinese-version microblog service. The system provides an intuitive and powerful retweet tree visualization which inspires users’ creativity. The expert system adopts public users’ analysis results collected from the web interface, and can visualize and analyze Weibo events to a deeper extent.



R-Map is a visual analytical approach with a map metaphor to support interactive exploration and insight analysis of the process of information reposting in social media. In R-Map, the reposting tree structure can be spatialized with highlighted key players and tiled nodes. The important reposting behaviors, the following relationships, and the semantic-changing relationships are represented as rivers, bridges, and routes, respectively, in a virtual geographical space.



D-Map is a novel visualization method to support exploration and analysis of social behaviors during such information diffusion and propagation on typical social media through a map metaphor. In D-Map, users who participated in reposting one central user’s posts are collected and mapped to a hexagonal grid based on their behavior similarities and in chronological order of the repostings. With additional interaction and linking, D-Map is capable of providing visual portraits of the influential users and describing their social behaviors.



E-Map is a visual analytics approach that uses map-like visualization tools to help multi-faceted analysis of social media data on a significant event. E-Map transforms extracted keywords, messages, and reposting behaviors into map features such as cities, towns, and rivers to build a structured and semantic space for users to explore. It also visualizes complex posting and reposting behaviors as simple trajectories and connections that can be easily followed.



WeiboGeo is an interactive visual analytics system to support the exploration of sparsely sampled trajectory data from social media. It is based on a heuristic model to reduce the uncertainty caused by the nature of social media data. By iteratively analyzing filtered movements, users can explore the semantics of movements, including the transportation methods, frequent visiting sequences and keyword descriptions.


Copyright 2012-2019, Peking University, All rights reserved.