Visualizing Time-Varying Topics Via Images and Texts for Inter-Media Analysis

Abstract

This paper proposes a system for analyzing societal behaviors by visualizing time-varying topics in multiple media. Various types of content such as text, images, and videos have spread throughout multiple media, such as TV and the Web, that have complementary information and influence one another. It is important to compare how these media react to real world events to understand recent societal behaviors and how each medium reacts to other media. Our system visualizes flows of content in multiple media in 3D space enabling us to simultaneously explore them. We present two example applications using our system. The first involves the visualization of inter-media events comparing the exposure of topics in TV news and the activities of bloggers. The second example application is a system for visualizing visual trends on social media that chronologically displays extracted clusters of images on blogs. The proposed systems enable users to visually monitor changes in thought, activities, and interests of people, and differences between media through interactively exploring flows of texts and images extracted from the media.