You should be able to open the PDF files now. Let me know if you still have problems. ... View more

I guess my question back would be whether you have changed any of them to "user topics".  If you make any change to a topic, such as its name, any of the topic weights, the term or document cutoff, then the topic is changed into a user topic.  Then when you generate new multi-term topics, it intentionally eliminates the one that is closest to the topic you have modified: that way you don't have to look at essentially the same topic twice.  Does this correspond to what you are seeing? ... View more

Here is installation guide and users guide for your perusal, if you want to see what the node will be able to do.  ... View more

Unfortunately, the Text Miner nodes do not work with  the Start/End group nodes.  Sorry! ... View more

the <nodename>_validout and _testout tables contain the tfidf weightings for the validation and test set respectively. ... View more

You are exactly right, the transaction table is the TFIDF table.  If you want to see it as term|role combinations, you can do something like the following with code or in code node (assume that this is on the first diagram, and the first text filter node on that diagram: %let filternode_name=emws1.textfilternode; %let viewname=<whatever data set you want to create>;    proc sql noprint;       create view &viewname as        select ktrim(term) || '|' || role as _item_, b.*        from &filternode_name._term_strings as a, &filternode_name._out_parent as b        where b._termnum_=a.key;          quit; ... View more

It sounds like you have a good handle on the differences between roll-up terms and SVD. You are correct that the SVD variables can be difficult to interpret, however, we have found in many applications that you can build a more effective model using them rather than roll-up terms, so there is a tradeoff. I will be looking forward to seeing what kind of results you get from this. It sounds like a very interesting applicaition. Jim Cox, Development Manager for SAS Text Miner ... View more