Temporal Exploration in 2D Visualization of Emotions on Twitter Stream

Abstract

As people freely express their opinions toward a product on Twitter streams without being bound by time, visualizing time pattern of customers emotional behavior can play a crucial role in decision-making. We analyze how emotions are fluctuated in pattern and demonstrate how we can explore it into useful visualizations with an appropriate framework. We manually customized the current framework in order to improve a state-of-the-art of crawling and visualizing Twitter data. The data, post or update on status on the Twitter website about iPhone, was collected from U.S.A, Japan, Indonesia, and Taiwan by using geographical bounding-box and visualized it into two-dimensional heat map, interactive stream graph, and context focus via brushing visualization. The results show that our proposed system can explore uniqueness of temporal pattern of customers emotional behavior.