Discovering and understanding the temporal evolution of events hidden in text corpora is a complex yet critical task for knowledge discovery. Although mining event dynamics has been an important research topic leading to many successful algorithms, researchers, research and development managers, intelligence analysts and the general public are still in dire need of effective tools to explore the evolutionary trends and patterns. This exploratory project focuses on developing and validating a novel idea called narrative animation. Narrative animation uses animated visualizations to narrate, explore, and share event dynamics conveyed in temporally evolving text collections. Film art techniques are employed to leverage the animated visualizations in information organization and change detection, with the goals of enhancing analytical power and user engagement. A prototype system called CityStories is being developed to generate narrative animations of events in cities derived from web-based text.
If this novel, risky research is successful, it is expected to yield fundamental results in narrative animation that can advance the current paradigm in information visualization and visual analytics by developing novel techniques in using animations for presenting and analyzing dynamic abstract data at a large scale. The pilot system CityStories system is expected provide a novel network platform for education, entertainment, and data analytics. It will engage general users such as students, teachers, journalists, bloggers, and many others in web information visualization and study. Results of this research will be disseminated through publications, the World Wide Web, and collaborations with researchers and analysts. The project web site (http://coitweb.uncc.edu/~jyang13/narrativeanimation/narrativeanimation.htm) will include research outcomes, publications, developed software, videos, and datasets for wide dissemination to public.
