Grants:IEG/AutomaticCategorization

From Meta, a Wikimedia project coordination wiki
This is an archived version of this page, as edited by He7d3r (talk | contribs) at 19:01, 3 October 2014 (→‎Measures of success: proper list; capitalization). It may differ significantly from the current version.
statusproposed
AutomaticCategorization
summaryThe idea is propose with machine learning techniques categories for an article in wikipedia.
targetMediawiki
strategic priorityimproving quality
amount1200 euros
granteedavidam
advisordavidam
contact• davidam@es.gnu.org
volunteerdavidam
this project needs...
volunteer
join
endorse
created on05:24, 28 September 2014 (UTC)
2014 round 2



Project idea

What is the problem you're trying to solve?

To improve the quality maybe useful suggest categories automatically.

What is your solution?

From a technical point of view, we must improve the interface to edit articles and match the article to another articles with a machine learning algorithm

Project goals

Improve the quality of wikipedia.

Project plan

Activities

I've experimented with NLTK to make automatic clasification of texts. I must implement some ideas about text clasification with php in mediawiki.

Budget

  • Travels to universities or free software meetings to exchange points of view: 1200 euros
  • Total Budget: 1200 euros

Community engagement

I am a member of the spanish chapter of wikimedia, there are meeting in this sense. I've worked in the university for a good number of years. I know good researchers in machine learning field.

Sustainability

It will be very interesting improve the algorithms, when become part of wikipedia, with the interaction of the users.

Measures of success

  1. It runs.
  2. The MediaWiki community has accepted the contribution.
  3. The Wikipedia community has accepted the contribution.
  4. Many users is using the feature. I could use a tracking system for it, or see logs.


Get involved

Participants

  • davidam: I've worked in UNED for many years deploying the current e-learning system, reaching articles and software for the university. Currently, I maintain software in GNU/Emacs [1], [2] and [3] and Drupal for Drupal.

Community Notification

Please paste links below to where relevant communities have been notified of your proposal, and to any other relevant community discussions. Need notification tips? http://www.wikimedia.es


Endorsements

Do you think this project should be selected for an Individual Engagement Grant? Please add your name and rationale for endorsing this project in the list below. (Other constructive feedback is welcome on the talk page of this proposal).

  • Community member: add your name and rationale here.