Mailing List Archive: 49091 messages
  • Home
  • Script library
  • AltME Archive
  • Mailing list
  • Articles Index
  • Site search

Text Mining, Summarizers, Bayesian learning

 [1/2] from: reboler::bol::com::br at: 18-Feb-2004 16:38

Hi Folks!, Is there anybody developing tools or algorithms in Rebol for text processing such as: clustering; stopwords and steaming; summarizing; or bayesian learning for social networks ? Anybody? thanks in advance, --DJ

 [2/2] from: Mike:withforesight at: 18-Feb-2004 23:17

This is not in Rebol but if you are looking for algorithms to do clustering you might what to see this article by M. E. J. Newman and M. Girvan: "Finding and evaluating community structure in networks" . The PDF is here: The authors claim the algorithms presented take O(mn) operations on a graph with m edges and n vertices. They also suggest their approach is tractable for networks of up to 10,000 nodes. The algorithm is fairly straight forward and could be implemented by a competent Rebol programmer (which rules me out). Also, a good review of the (fast growing) literature on this topic was done in 2003 by Newman: "The structure and function of complex networks" and can be found here: HTH Mike Behar