Pagerank-Like Algorithm for Ranking News Stories and News Portals
News websites are one of the most visited destinations on the web. As there are many news portals created on a daily basis, each having its own preference for which news are important, detecting unbiased important news might be useful for users to keep up to date with what is happening in the world. In this work we present a method for identifying top news in the web environment that consists of diversified news portals. It is commonly know that important news generally occupies visually significant place on a home page of a news site and that many news portals will cover important news events. We used these two properties to model the relationship between homepages, news articles and events in the world, and present an algorithm to identify important events and automatically calculate the significance, or authority, of the news portals.
Keywordsnews ranking pagerank portals
Unable to display preview. Download preview PDF.
- 1.Newspaper Association of America (2009), http://www.naa.org/News-and-Media/Press-Center/Archives/2009/Newspaper-websites-attract-more-than-70-million-visitors.aspx
- 3.Allan, J.: Topic Detection and Tracking. Kluwer Academic Publishers (2002)Google Scholar
- 4.Allan, J., Carbonell, G., Doddington, J., Yamron, J., Yang, Y.: Topic detection and tracking pilot study: Final report. In: Proceedings of the Broadcast News Understanding and Transcription Workshop, pp. 194–218 (1998)Google Scholar
- 5.Allan, J., Lavrenko, V., Jin, H.: First story detection in TDT is hard. In: Proceedings of the Ninth International Conference on Information and Knowledge Management, pp. 374–381 (2000)Google Scholar