Submissions/The Revision Scoring Service -- Exposing Quality to Wiki Tools
This is an accepted submission for Wikimania 2015. |
- Submission no.
- 3047
- Title of the submission
- The Revision Scoring Service -- Exposing Quality to Wiki Tools
- Type of submission (discussion, hot seat, panel, presentation, tutorial, workshop)
- presentation
- Author of the submission
- Aaron Halfaker, とある白い猫
- E-mail address
- ahalfaker@wikimedia.org
- Username
-
- EpochFail (Volunteer)
- Halfak (WMF) (Staff)
- Country of origin
- USA
- Affiliation, if any (organisation, company etc.)
- Wikimedia Foundation
- Personal homepage or blog
- http://halfaker.info
- Abstract (at least 300 words to describe your proposal)
Wikipedia relies heavily on artificial intelligence (AI) to operate at the scale that it does today. The use of AI is most apparent in counter-vandalism tools, like those used to revert nearly all the vandalism on the English Wikipedia: ClueBot NG, Huggle and STiki. These advanced wiki tools use intelligent algorithms to automatically revert vandalism (ClueBot NG) or triage likely damaging edits for human review (Huggle and STiki). It's arguable that these tools saved Wikipedia from being overwhelmed by the massive growth period of 2006-07.
Regretfully, developing and implementing such powerful AI is hard. A developer needs to have the expertise in machine classification, natural language processing, and advanced programming techniques as well as hardware to store and process large amount of data. It's also relatively labor intensive to maintain these AI so that they stay up to date with the quality concerns of present day Wikipedia. Likely due to these difficulties, AI-based quality control tools only are available for English Wikipedia and a few other, large wikis.
In this presentation, I'll talk to you about how things can be better. First, I'll give an overview of a project that is designed to make a critical bit of AI accessible to wiki tool builders. Next I'll highlight strategies that I think will be important for making sure these resources stay valuable long-term. Finally, I'll conclude with an overview of how Wikipedia's current tools and resources might take advantage of artificial intelligence resources right now.
- Track
- Technology, Interface & Infrastructure
- Length of session (if other than 30 minutes, specify how long)
- 30 minutes
- Will you attend Wikimania if your submission is not accepted?
- yes
- Slides or further information (optional)
- Special requests
- If possible, please schedule in a session together with Submissions/Would you like some artificial intelligence with that? with this presentation afterwards.
Interested attendees
If you are interested in attending this session, please sign with your username below. This will help reviewers to decide which sessions are of high interest. Sign with a hash and four tildes. (# ~~~~).
- Daniel Mietchen (talk) 03:24, 15 February 2015 (UTC)
- Mrjohncummings (talk) 05:28, 16 February 2015 (UTC)
- Jaredzimmerman (WMF) (talk) 08:55, 23 February 2015 (UTC)
- Sage (Wiki Ed) (talk) 01:06, 25 February 2015 (UTC)
- Jean-Frédéric (talk) 09:06, 25 February 2015 (UTC)
- Asaf (WMF) (talk) 02:44, 28 February 2015 (UTC)
- guillom (talk) 00:05, 8 March 2015 (UTC)
- --Ilya (talk) 22:56, 9 March 2015 (UTC)
- Quiddity (WMF) (talk) 05:05, 26 March 2015 (UTC)
- eranroz (talk) 08:16, 4 July 2015 (UTC)
- Add your username here.