I have an example set which has one column text with UTF8 encoding (Title of news articles) and I want to cluster news articles based on their title. With which operator can convert UTF8 to plain text.
BTW, titles are in the German language.
I really appreciate if someone can help. Thank you
RM can handle different encoding types, you can set this in the Preference dialog. First thing though, in what format are these files? If they are text, then you can use Process Documents from File operator (Text Processing extension) or Open File. Do you plan on doing tokenization or some sort of entity extraction?
The following 6-part video series is probably still one of the best resources about how to do those kind of analyses with RapidMiner:
Hope this helps,