The data analysis for the facts and figures below consists of two stages:

  1. Taking compressed complete dumps of the English wikipedia and processing them to extract citation needed tags
  2. Analyzing the extracted tags in R.

The processing was done in Java with use of the WikiXMLJ package by Google. Information on the processing can be found in the README.

This document was generated from a markdown file including all analysis, Analysis.Rmd.

Histogram for 2013 data:

Histogram for 2015 data:

Other interesting information: