Talk:Text mining
From Wikipedia, the free encyclopedia
[edit] Identifying link spam
What are the relevant guidelines for deciding when something is link spam? It like many of the external links are posted by people with vested interest. Some of the sites are truly helpful in understanding what text mining is, whereas others are really about general NLP or information extraction, and some look suspiciously like SEO or ad nests. -Serapio 05:23, 6 June 2006 (UTC)
- Have a look at: WP:SPAM and Wikipedia:Wikiproject no ads and user with the following contributions is now warned: Special:Contributions/24.6.82.35. He/She added unspecific external link out's, so since this far from being neutral I have already deleted some of them. Even for more general topics like data mining and machine learning the links are questionable.
- JKW 18:22, 6 June 2006 (UTC)
[edit] Applications
Could someone with more expertise in the subject than I add to the Security and Commercial applications subsections, and possibly write a better introduction to the applications section in general? Thank you! -Hobbes 10:10, 13 Jun 06
[edit] Commercial Software
Can we add a list to the bottom of this page of commercial software vendors that provide text mining software? I don't see why we shouldn't provide pointers to solution providers in this space. There are lots of toolkits and academic (free) packages listed, but many readers of this page may be looking for something more packaged. We've added some links to vendors before, only to have them agressively removed by other users. Many other similar pages to this text mining page list companies who provide products in the area that the pages refer to. Can we agree to add a list of commercial links at the bottom of this page, for people who are looking for commercial text mining packages, without having it continuously deleted by other users?
There is still a problem of spam with External links. Some links are removed and we still see other commercial links. According to Wikipedia Policies and guidelines we must remove all commercial software vendors here (for example Topicalizer and Textalyser) or include more vendors in the list (for example Clearforest, Semantic-knowledge, SPSS). What's up? —Preceding unsigned comment added by 81.66.159.36 (talk • contribs) 18:43, 22 November 2006
- That seems like a sensible idea. Consistency should prevail. —Preceding unsigned comment added by 81.247.173.243 (talk • contribs) 12:59, 26 April 2007
- All of the links have been removed. Is there still a problem? --Ronz 14:36, 26 April 2007 (UTC)
- I think it is fine now. We need now rather more information on general tests for text mining and object extraction (there are some free documents available) and perhaps add more on standard methodologies used.Periergeia
- All of the links have been removed. Is there still a problem? --Ronz 14:36, 26 April 2007 (UTC)
This list continues to attract spam and non-notable entries. To manage this, I think we need to follow WP:LIST by having inclusion criteria. Until we come up with something better, we should only list entries that have their own articles. --Ronz (talk) 03:37, 8 December 2007 (UTC)
