New software tool makes competences measurable in learning games


In his research, Georgiadis discusses the development of Smart CAT, a software tool that provides an automatic assessment of skills by making smart use of the digital traces a student leaves in a game or other digital environments. This method is known as Stealth Assessment (hidden assessment): you are not assessed via a separate test, but on the behavior and actions that emerge from the digital traces.

Stealth Assessment

The assessment method used is based on the one hand on Evidence Centered Design, a systematic way of describing and measuring competences. On the other hand, Stealth Assessment makes use of Machine Learning Technology, the ability of computers to recognize patterns and thus – in this case – draw conclusions about the command of the required competences. Until now, however, the application of Stealth Assessment has been a complex, time-consuming and labor-intensive process. Georgiadis shows in his thesis that the Smart CAT software can overcome these barriers and lead to wider application.

Smart CAT software

The Smart CAT software helps users design a Stealth Assessment application and automatically performs the analyzes necessary to arrive at an assessment. Tests with two separate serious games have shown that the assessments given by Smart CAT are valid and very accurate. Computer simulations have also shown that the results are very stable under a wide variety of test conditions. Smart CAT is seen by end users (teachers and assessors) as a very useful and user-friendly tool. Georgiadis’ dissertation offers a new perspective on data-based assessments in serious games. In this way, the research contributes to the educational value of serious games and their use in regular education.

Georgiadis will defend his thesis ‘Smart CAT: Machine Learning for Configurable Assessments in Serious Games’ on Friday, October 2.

By: National Education Guide

Source link by

*The article has been translated based on the content of Source link by
. If there is any problem regarding the content, copyright, please leave a report below the article. We will try to process as quickly as possible to protect the rights of the author. Thank you very much!

*We just want readers to access information more quickly and easily with other multilingual content, instead of information only available in a certain language.

*We always respect the copyright of the content of the author and always include the original link of the source article.If the author disagrees, just leave the report below the article, the article will be edited or deleted at the request of the author. Thanks very much! Best regards!


Please enter your comment!
Please enter your name here