@article{Boley97principaldirection,
  abstract = {We propose a new algorithm capable of partitioning a set of documents or other samples based on an embedding in a high dimensional Euclidean space (i.e. in which every document is a vector of real numbers). The method is unusual in that it is divisive, as opposed to agglomerative, and operates by repeatedly splitting clusters into smaller clusters. The splits are not based on any distance or similarity measure. The documents are assembled in to a matrix which is very sparse. It is this sparsity that permits the algorithm to be very efficient. The performance of the method is illustrated with a set of text documents obtained from the World Wide Web. Some possible extensions are proposed for further investigation.},
  author = {Boley, Daniel},
  interhash = {281afd06bd3e21ec3ef212da4ec18ee0},
  intrahash = {bca740460f14035af773f665887b6fa4},
  journal = {Data Mining and Knowledge Discovery},
  pages = {325--344},
  title = {Principal Direction Divisive Partitioning},
  volume = 2,
  year = 1997
}