OpinionFlow: Visual Analysis of Opinion Diffusion on Social Media

Abstract

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.

CiteRivers: Visual Analytics of Citation Patterns

“…Extended versions show thematic changes and interaction between topics in text datasets [13], and tag clouds have been used as topic labels [48]. Dou et al [15] embed them into a tree structure to allow for the exploration of hierarchical topics, and Wu et al [52] combine them with a visualization of sentiment analysis results encoded by color. We extend streamgraphs with a flowgraph-based exploration technique.…”

Spatial–temporal visualization of city-wide crowd movement

“…Outflow Wongsuphasawat and Gotz (2012) focused on the aggregation and display of multiple event sequences and their state transitions, and Xu et al Xu et al (2013) introduced a visual analysis system that explores topic competition in social media and the influence of opinion leaders. Wu et al Wu et al (2014) also focused on the diffusion of opinions and developed a visual analytics system to measure opinion propagation among Twitter users and FluxFlow Zhao et al (2014) focused on the analysis of anomalous information spread. Sun et al Sun et al (2014) modeled the competition process among topics by measuring the influence of topic leaders and designed a time-based visualization, EvoRiver, to explore such interactions.…”

What is in a Rumour

“…Wu et al [16] presented OpinionFlow which utilized information diffusion theories to visualize how opinions are disseminated by Twitter users through the adoption of Sankey diagram and a tailored density map. Users can select multiple topics from a stacked tree of topics to compare their diffusion patterns on Twitter.…”

“…The Sankey graph based on this connection allows the viewers to perceive the volume of migration of users from one topic to another along the rumour life cycle. Sankey graphs have been used before to visualize topic flows in OSNs [16], though with a construction based on influence models, instead of topic changes.…”