Readability of the Web

A study on 1 billion web pages.

by Marije de Heus

Automated Readability Index for the Web

We have performed a readability study on more than 1 billion web pages. The Automated Readability Index was used to determine the average grade level required to easily comprehend a website. Some of the results are that a 16-year-old can easily understand 50% of the web and an 18-year old can easily understand 77% of the web. This information can be used in a search engine to filter websites that are likely to be incomprehensible for younger users.

To be presented at the 13th Dutch-Belgian Information Retrieval Workshop DIR 2013 on 26 April in Delft, The Netherlands

[download pdf]