Celebrity Watch: Browsing News Content by Exploiting Social Intelligence

  • Omar Ali
  • Ilias Flaounas
  • Tijl De Bie
  • Nello Cristianini
Conference paper

DOI: 10.1007/978-3-642-23808-6_40

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6913)
Cite this paper as:
Ali O., Flaounas I., De Bie T., Cristianini N. (2011) Celebrity Watch: Browsing News Content by Exploiting Social Intelligence. In: Gunopulos D., Hofmann T., Malerba D., Vazirgiannis M. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011. Lecture Notes in Computer Science, vol 6913. Springer, Berlin, Heidelberg

Abstract

Celebrity Watch is an automatically-generated website that presents up-to-date entertainment news from around the world. It demonstrates the application of many pattern analysis methods that allow us to autonomously monitor millions of news articles and hundreds of millions of references to people mentioned in them. We apply statistical methods to merge references into people, track their association to various topics of news, and generate social networks of their co-occurrences in articles. From this sea of data we select the forty most-relevant people and display them on the website, offering users a highly condensed view of the latest in entertainment news. The site updates itself throughout the day and is the final step in a large, fully-autonomous system that monitors online news media.

Keywords

news mining statistical inference trend detection social networks entertainment news 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Omar Ali
    • 1
  • Ilias Flaounas
    • 1
  • Tijl De Bie
    • 1
  • Nello Cristianini
    • 1
  1. 1.Intelligent Systems LaboratoryBristol UniversityBristolUnited Kingdom

Personalised recommendations