I've been using the text processing package for RapidMiner and am currently trying to do clustering and association rules with text documents. I've followed all of the steps in this Vancouver Data help video (http://vancouverdata.blogspot.com/2010/11/text-analytics-with-rapidminer-part-3.html) and built the exact same process, but have not been able to generate results. When I try to run the process, it runs for around 20-30 minutes (as opposed to a few seconds on the video) before telling me that I have run out of memory. I'm not dealing with large documents, only two small text files. I allocated 4GB to the program so memory shouldn't be an issue, but I keep getting this error message. A similar thing happens with any other clustering process I try to do.
Does anyone have any advice as to how to solve the problem?