Currently tag "text-mining" has a definition that somehow mixes up data mining on text and text classification. Also, there is no other general tag like "text-analysis" that covers the broader field. In my mind that broader field includes e.g. clustering of text, feature extraction, preprocessing etc.

Since we do have general application tags like image-processing or clinical-trials that cover all different aspects of the corresponding applications shouldn't we have something similar for text? It would help better annotate questions that can be answered by experts of the field.

I propose renaming the text-mining tag to text-analysis and provide a more general/loose definition.

  • 1
    $\begingroup$ I don't see the need for this. Bear in mind that I don't do text mining, so maybe I'm wrong, but I think of classification, clustering, feature extraction, etc. as parts of data mining. Thus by analogy, I would see text classification, clustering of text, etc. to be parts of text mining. I do recognize that certain text preprocessing tasks like parsing & turning words into stems are more like data cleaning than prototypical data mining, though. So if there are enough Q's to support it & people think [text-mining] is too heterogeneous, we could have [text-preprocessing] as well. $\endgroup$ Feb 2, 2014 at 3:45


You must log in to answer this question.

Browse other questions tagged .