Paper abstract

For anyone who's interested. I want to take this opportunity to repeat my thanks to those people who suggested directions to go in when I asked for help earlier this year.

In recent years, major news corporations seem to dedicate an increasing amount of time and space to "fluff," reporting on celebrities, entertainment and crime stories, rather than more essential national and international news. As such news content is increasingly gathered online, it has become feasible to aggregate large amounts of data from a wide range of sites. This report proposes a model for collecting information from news agencies, then applying the techniques of Data Mining to organize this reporting in a way that identifies the priorities of individual organizations.

In addition, the rise of user-based taxonomies has made it possible broadly to evaluate the interests of people who actively read and recommend news. In the final analysis, data collected from users of Digg.com are compared with data collected from media sites. This provides a benchmark for determining whether the delivery of "fluff" news is delivered is a fair response to popular demand, or whether typical news readers are dissatisfied with the level of serious event coverage found in the media.