MP4 Format: "MP4"
QuickTime Format: "MOV"
The proliferation of online social media provides people a new platform to effectively spread opinions and ideas during
political or marketing campaigns. In the campaign process, people generate and propagate their opinions to either support or
challenge the campaign objectives shared by relevant social groups, which often lead to public conflicts. Different social groups'
responses to these opinions usually contain distinct sentiments, of which the distinctiveness reflects the intensity of the conflicts.
An intuitive visualization that allows for unfolding the process of a public conflict from the rich and massive social media data will
have far-reaching impact in various domains including social, political and economic. In this paper, we propose the first visualization
system, SocialHelix, to achieve this goal. SocialHelix incorporates a novel visual design which enables users to detect and trace
public conflicts occurring in social media, and to understand when and why conflicts occurred and how they evolved among different
social groups. In our design, the time-evolving, complex interaction of various sentiments between social groups is conveyed based on
the metaphor of a DNA molecule, where the distinctive sentiments of two groups are captured and represented as sentiment streams
that look like double-stranded helices. For our visualization purpose, we propose sentiment-based conflict analysis algorithms to
effectively identify social groups with coherent sentiment trends. We demonstrate the effectiveness and usefulness of SocialHelix by
conducting in-depth case studies and user interviews based on Twitter data regarding to the national political debates.