The research group behind Wikipedia, Wikimedia Research, recently teamed up with computer scientists from Stanford University to hone in on the language gaps of the website. Wikipedia noted their work in a blog post on April 27.

"Each day, thousands of volunteer editors are filling knowledge gaps by creating new Wikipedia articles, translating existing ones, and identifying poorly covered topics in any given language," said Leila Zia and Dario Taraborelli of the Wikimedia Foundation.
"However, discovering and deciding what to edit can be a daunting task, both for editors who are new to Wikipedia and for more-seasoned ones."

Wikipedia went on to say that millions of articles across its website are missing across various language editions. This is where the research team came in to play.

Wikimedia Research and Stanford researchers designed a system geared toward finding, ranking and recommending missing articles to be created across various languages. In a controlled test on the French-language Wikipedia, the system showed promise. 

"By comparing personalized recommendations and non-personalized recommendations against a baseline: our results show that recommendations tripled the rate at which editors create articles, while maintaining the same level of article quality as articles created organically in French Wikipedia," Zia and Taraborelli concluded.

Following the initial results, Zia and Taraborelli were joined by software developers and designers to create a prototype of an article recommendation tool. It utilizes a simplified version of the original algorithm they created, based on search, page view and Wikidata APIs. This information helps identify trending articles in a given source language and missing in a target language. 

Other features of the prototype include a search function that allows users to find recommendations based on specific topics, and an API that helps create new articles by translating pages from one language to another.

"Over the coming months, we will be monitoring the tool closely to learn more about how it's being used by editors and how it can be further improved," wrote Taraborelli and Zia.

The researchers add that they're interested in seeing how the prototype can be used by groups participating in meetups, edit-a-thons, and reach-out events. Users can provide feedback on the tool on Wikimedia discussion page.

ⓒ 2021 All rights reserved. Do not reproduce without permission.