Todd Grappone
Associate University Librarian for Digital Initiatives and Information Technology
University of California, Los Angeles
Sharon E. Farb
Associate University Librarian for Collection Management and Scholarly Communication
University of California, Los Angeles
Rapidly changing technologies of multi-modal communication are transforming the news industry: from the global reach of international satellite TV, to the proliferation of Internet news outlets, to YouTube. In parallel, “citizen journalism” is on the rise, enabled by smart phones, social networks, and blogs. The Internet is becoming a vast information ecosystem driven by mediated events (elections, social movements, natural disasters, disease epidemics, etc.) with rich heterogeneous data: text, image, and video. Meanwhile, the tools and methodologies for users and researchers are not keeping pace: it remains prohibitively labor-intensive to systematically access and study the vast amount of emerging audiovisual news data.
This presentation reviews and demonstrates applications of the Broadcast News Archive from the University of California Los Angeles (UCLA) Library, a cross-disciplinary National Science Foundation-funded effort to digitize, analyze, and make available an unprecedented news resource for researchers worldwide. Leveraging UCLA Library’s growing digital collection of 150,000 hours of television news videos, including 9.7 billion image frames and 802 million words of closed captioning news text directed by the Communication Studies Department at UCLA and curated by the UCLA Library, a new paradigm is proposed for analyzing audiovisual datasets of social and political news events. Of note in the Archive is a Text and Image Parsing Project which has as its aims the categorization of news by topics and events; the analysis of selection and presentation biases across networks and media spheres in a statistical and quantitative manner; the experimental investigation of the cognitive consequences of concordant and discordant audio/visual information streams; and, modeling of the techniques of verbal and visual persuasion. More broadly, the project endeavors to reveal agenda-setting trends in the news, and uncover spatiotemporal patterns in the interactions of multiple mediated events. Through the interactive news interface, researchers will have the ability to visualize and interact with the project’s computation and statistical results.