Research:AFTRank

Created
2012/12
Contact
Ryan Faulkner
Collaborators
Aaron Halfaker
Oliver Keyes
Dario Taraborelli
Duration:  2012-12 – 2013-
Incomplete-document.svg

This page is an incomplete draft of a research project.
Information is incomplete and is likely to change substantially before the project starts.


Key PersonnelEdit

  • Ryan Faulkner
  • Aaron Halfaker
  • Oliver Keyes
  • Dario Taraborelli

Project SummaryEdit

This project aims to develop and test a classifier to identify good feedback from a corpus of unmoderated/non-featured article feedback (v.5) posts. The design goals of AFTRank are the following:

  1. reduce the workload of feedback moderators by prefiltering feedback not worth being moderated:
    1. automatically hide or decrease the score of bad feedback without the need of hitting AbuseFilter
    2. increase the score of unmoderated good feedback
  2. correct the bias towards high-traffic articles produced by the current UI of the FeedbackPage:
    1. allow moderators to explore the large amount of feedback from low-traffic articles that hardly receives any attention
    2. surface feedback from articles with an expected higher feedback quality but low moderation activity

MethodsEdit

DisseminationEdit

Wikimedia Policies, Ethics, and Human Subjects ProtectionEdit

Benefits for the Wikimedia communityEdit

TimelineEdit

FundingEdit

ReferencesEdit

External linksEdit

ContactsEdit