RadioPlus Context Browser


Contextualize RSS feeds with content

Radio can be much more then listening only. Radio can be made searchable to find a certain quote, person or topic. The experience of listening radio can be enhanced presenting related images from other information sources on a screen. Reversely, radio content can also be linked to information on the web. A written news story might be enriched with a related radio interview. We improve the use and experience of radio content by automatically processing audio files and combining the output with the latest audio search technology.

In this first version prototype we explore the possibilities of automatically linking news items to relevant audiovisual content in an archive, in this case radio content. For example when there is a news item on a novelist winning an award, the system should provide the user with relevant radio content such as a radio interview with the novelist, or radio items discussing this award.

Three important factors influence the quality of the system:

  1. the size of the underlying database with archive content (in a small database it will be hard to find relevant content for a given news item);2. the type of content in the underlying database (in a collection of in-depth interviews on cultural topics it will be less probable to find content related to a sports news event);
  2. the quality of the linking technology.

The technology is connected to the platform: a collection of historical and recent radio stories. Partners in our work are media industry representatives: content-owners (VPRO), archives (S&V) and technology providers (Cross-Media Interaction). In this application, one of the main difficulties is to automatically extract those keywords from the news text that have the best chance of finding relevant content in the available database.