Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Towards a diversity-minded Wikipedia


Published on

Published in: Technology, Business
  • Be the first to comment

  • Be the first to like this

Towards a diversity-minded Wikipedia

  1. 1. Towards a diversity-minded Wikipedia Fabian Flöck, Denny Vrandecic, Elena Simperl – KIT Karlsruhe
  2. 2. The loss of viewpoint diversity
  3. 3. Wikipedia is biasedo To what extend does Wikipedia represent all relevant PoVs?o Neutral-point-of-view policyo Examples: Conservapedia, Croatian and Serbian editions
  4. 4. Leveraging diversity in WikipediaUse Case - In collaboration with Wikimedia Germany: Displaying warnings when detecting patterns of bias in editing behaviorChallenge: Identify, understand and predict socio-technical mechanisms leading to bias
  5. 5. Context: Slowing growth and content saturation • Less new articles, less edit Total active editors per month growth since 2007 (Thousands) • Consolidation of articles • No room for easy contribution New articles per month on Revert ratio per month by editor classFigures by Suh et al.“The Singularity is not near: Slowing growth of Wikipedia”
  6. 6. Socio-technical mechanisms leading to biaso Consensus: social proof and consolidationo Ownership behavioro Opinion camps and editor drop-outo Boldness and useful conflictso Bureaucracy and implicit social normso Personal characteristics of authorso WikiProjects and other groups
  7. 7. Building a bias prediction model1. Identify typical patterns for a socio-technical mechanisms2. Evaluate if these patterns are typical for articles marked as “biased”3. Train machine learning algorithms to predict bias using the patterns
  8. 8. Building a bias prediction model1. Finding patterns:o Ownership behavior • Typical patterns in “Maintained” articles  High # of reverted newcomers  High concentration of edits, reverts  Core high-activity-editor group  … • Methods  Statistical analysis on revision history, etc.  SNAo .. And for all the listed mechanisms
  9. 9. Conclusiono Building a prediction model as complete as possibleo Converge with other models developed for Wikipedia in RENDER Build tools that help the shrinking number of editors to copewith the work overload of finding and curing bias