WIN Webinar: Measuring the quality of large-scale automated classification systems applied to online job advertisements data, 5 March 2024

Muhammad Suffian
Muhammad Suffian • 5 April 2024
Image of the webinar's first slide, highlighting the title and speakers

This webinar provided insight into the quality and usability of web-scraped data for producing official statistics. The quality assessment in the presentation was about online job advertisements (OJAs). 

The OJA data was assessed in a number of ways by members of the WIN project. 

Firstly, the quality and stability of the sources were evaluated with the help of quality indicators formulated for this task. 

Secondly, the accuracy of the classification of the OJA data was assessed through annotation exercises. 

The presentation showed the quality indicators and how they are operational in a reproducible manner for several countries.

The learning objectives included:

  • demonstrating quality indicators for assessing the quality of sources and the quality of estimated classifications.

Watch the webinar here

Download the slides here

 

Be the first one to comment


Please log in or sign up to comment.