NEWS HUNTER: BUILDING AND MINING KNOWLEDGE GRAPHS FOR NEWSROOM SYSTEMS

  • Arne Berven Wolftech Broadcast Solutions
  • Ole A Christensen University of Bergen
  • Sindre Moldeklev University of Bergen
  • Andreas L Opdahl University of Bergen
  • Kjell J Villanger University of Bergen

Abstract

Journalism is challenged by digitalisation and social media, resulting in lower subscription numbers and reduced advertising income. Information and communication techniques (ICT) offer new opportunities. We are exploring how social, open, and other data sources can be leveraged for journalistic purposes through techniques such as knowledge graphs, natural-language processing (NLP), and machine learning (ML). Our focus is on how these and other heterogeneous data sources and techniques can be combined into a flexible architecture that can evolve and grow to support the needs of future digital journalists. The paper presents the current state of our architecture and its instantiation as a prototype we have called News Hunter. Plans and possibilities for future work are also outlined.

Published
2018-09-17