Talk:Concept mining

Linguistics: Applied Linguistics Low‑importance

	Linguistics portal This article is within the scope of WikiProject Linguistics, a collaborative effort to improve the coverage of linguistics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.LinguisticsWikipedia:WikiProject LinguisticsTemplate:WikiProject LinguisticsLinguistics articles
Low	This article has been rated as Low-importance on the project's importance scale.
	This article is supported by Applied Linguistics Task Force.

Taxonomic classification is not the same thing as concept mining. Although Concept Mining can be used for taxonomic classification, i.e. looking at a collection of documents, and inferring which taxonomic class they belong to, such taxonomies are normally constructed for a particular task, for instance a particular domain of medicine, whereas concept mining is concerned with generating analyses of greneral purpose documents based on the conceptual relationships in common speech. The uses of this analysis extend far beyond the librarianship applications of taxonomic classification. —The preceding unsigned comment was added by Scientio (talk • contribs) 15:21, 22 November 2006 (UTC).[reply]

I agree. Concept mining involves what data you look at when you're trying to understand a document's content (mapping words to concepts instead of using word counts directly) while taxonomic classification involves what you do with your understanding (placing documents into a predetermined tree, rather than grouping them into unhierarchical clusters, ranking them for relevance, or whatever else). The two concepts seem different enough that I see no justification for a merge. —David Eppstein 16:57, 23 November 2006 (UTC)[reply]

OK, I see your distinction. But if your talking about placing documents into a predetermined tree I think this is exactly concept mining, or at least Text classification, mapping of documents to concepts, which already exists in some given hierarchy, and ranking them for relevance, is more concept mining than taxonomic classification. From the definition of taxonomic classification, it sounds like it's the act of building the taxonomy. Roee 00:07, 29 November 2006 (UTC)[reply]

I thought "concept mining" was an associated concept for computer science? Yes, taxonomic classification is a hierarchical method of arrangement or classification but is a broad term not specific to computer science terminologies with many applications from biology to epistemology ... Stevenmitchell 00:47, 10 December 2006 (UTC)[reply]

MORE votes

I agree. Concept mining is not Taxonomy.. Concept mining is a relatively new term in information science/management for things we've been doing for hundreds of years. Unavoidably, concepts now defined by the term "concept mining" is assumed prerequisite in any classification, hence taxonomy. These two terms only overlap, BUT should remain separate, because each expands to other concepts not related to both, they are historically and functionally separate

More specific definition?

The definition in the first paragraph seems lacking. It seems to be talking about analyzing data in documents based on some sort of "concept map" (perhaps akin to Wordnet). i.e. for use in anti-plagiarism, documents would be compared based on "concepts" rather than exact words. true? Jjchong 11:52, 22 March 2007 (UTC)[reply]

I agree that the definition is vague and provides little context for the non-specialist reader. It's not clear what is meant by "concept", for instance. I arrived via the Formal Concept Analysis page and couldn't figure out (by just skimming the Concept mining page) if there is a relation. There's a link to the FCA page at the end, but I don't see it referenced in the text. Please be more specific in the text, provide examples. Thanks. 71.142.241.239 (talk) 03:10, 6 April 2008 (UTC)[reply]

No merger

It appears no one agrees that this article should be merged with taxonomic classification. Nor do I. I'm going to remove the merge template. Paul D. Anderson 01:33, 22 May 2007 (UTC)[reply]

Vs. Information extraction

How are these different? Should the topics be merged? ---- CharlesGillingham (talk) 22:41, 10 December 2007 (UTC)[reply]

Benefits section

I'm erasing this nonsense. Program size cannot be of any indication of the underlying algorithm's time complexity. —Preceding unsigned comment added by Kallikanzarid (talk • contribs) 01:45, 8 September 2010 (UTC)[reply]