For the past 73 years, the CBC has disseminated a unique Canadian perspective across the world, producing a phenomenally rich multimedia record of the country and our social, political and cultural heritage and news. This project utilizes visualization and sonification of portions of an enormous historical CBC Newsworld data corpus to enable an ‘on this day’ experience for viewers. The digitized collection of 24‑hour news videos spans a 23‑year period (1989‑2012) within an immersive multiscreen environment, to enable gesture‑driven context‑aware browsing, information seeking, and segment review. Employing natural language processing technologies, the interface displays keywords and key phrases identified in the transcripts, enabling serendipitous video search and display and offering a unique browsing opportunity within this rich ‘big data’ corpus. Goals ‑ The CBC Newsworld archives present a video corpus completely unlike any other that has been made available in searchable/browsable form. This project has three inter‑connected preservation and research goals. The first is to digitize, visualize, and make available this collection of 23 years of Canadian news broadcasts through a state‑of‑the‑art multimedia search and browsing system, to ensure its preservation and make it available as a valuable resource for researchers and students. The second goal is to design a real‑world project as an arena in which to conduct exploratory research and develop and test new technologies for video browsing, search and visualization, and spoken document and video retrieval. The third is to design and test an immersive environment and aesthetic interface design, employing gestural and touch interfaces for browsing this incredible corpus. This is a novel proposition for video browsing and serendipitous search, which to our knowledge is not currently available otherwise, which would have many applications for searching large spoken word news and video corpora.
- Martha Ladly, OCAD University, Toronto, CA