\begin{thebibliography}{10}

\bibitem{hadoop}
Hadoop: A distributed computing platform.
\newblock \url{http://lucene.apache.org/hadoop/about.html}.

\bibitem{mapred}
Jeffrey Dean and Sanjay Ghemawat.
\newblock Mapreduce: Simplified data processing on large clusters.
\newblock In {\em Sixth Symposium on Operating System Design and
  Implementation}, December 2004.

\bibitem{gfs}
Howard Gobioff, Shun-Tak Leung, and Sanjay Ghemawat.
\newblock The google file system.
\newblock In {\em Symposium on Operating System Principles}, October 2003.

\bibitem{cobra}
Ian Rose, Rohan Murty, Peter Pietzuch, Jonathan Ledlie, Mema Roussopoulos, and
  Matt Welsh.
\newblock Cobra: Content-based filterting and aggregation of blogs and rss
  feeds.

\bibitem{technorati}
Technorati.
\newblock \url{http://www.technorati.com/}.

\bibitem{blogstate}
David Sifry.
\newblock The state of the blogosphere.
\newblock \url{http://www.sifry.com/alerts/archives/000436.html}.

\bibitem{fabret}
Fran{\c{c}}oise Fabret, H.~Arno Jacobsen, Fran{\c{c}}ois Llirbat, Jo{\~a}o
  Pereira, Kenneth~A. Ross, and Dennis Shasha.
\newblock Filtering algorithms and implementation for very fast publish\slash
  subscribe systems.
\newblock {\em SIGMOD Record (ACM Special Interest Group on Management of
  Data)}, 30(2):115--126, 2001.

\bibitem{nutch}
Nutch: open source web-search software.
\newblock \url{http://lucene.apache.org/nutch/about.html}.

\bibitem{blogdigger}
Blogdigger.
\newblock \url{http://www.blogdigger.com/}.

\bibitem{mozdex}
Mozdex.
\newblock \url{http://www.mozdex.com/}.

\bibitem{glance}
N.~Glance, M.~Hurst, and T.~Tomokiyo.
\newblock Blogpulse: Automated trend discovery for weblogs.
\newblock In {\em WWW 2004 Workshop on the Weblogging Ecosystem: Aggregation,
  Analysis and Dynamics}, 2004.

\bibitem{blogpulse}
Blogpulse.
\newblock \url{http://www.blogpulse.com}.

\bibitem{ufp}
Universal feed parser.
\newblock \url{http://www.feedparser.org/}.

\end{thebibliography}