Oops... Didn't see ted's response before I had replied.. Sent from my iPhone
> On Feb 6, 2014, at 7:31 PM, Ted Dunning <ted.dunn...@gmail.com> wrote: > > OK. Cool. > > That probably means that problem is much smaller and more likely to be > logistics. Your suggestion of an off-by-one issue is quite plausible. > > > On Thu, Feb 6, 2014 at 4:46 PM, Stamatis Rapanakis > <stamrapana...@gmail.com>wrote: > >> That is correct. My problem is not the categories developed (which are >> meaningful by the way) but the fact that a certain document is not assigned >> to the proper (LDA generated) category. The document to topics assignment >> is really bad... >> >> >>> On Thu, Feb 6, 2014 at 5:08 PM, Ted Dunning <ted.dunn...@gmail.com> wrote: >>> >>> I can't comment on the specific question that you ask, but it should not >>> necessarily be expected that LDA will reconstruct the categories that you >>> have in mind. It will develop categories that explain the data as well >> as >>> it can, but that won't necessarily match the categories you intend. >>> >>> It is likely, however, that the topics that LDA derives would make a good >>> set of features for a classifier. >>