Beyond right or wrong: towards redefining adaptive learning indicators in virtual learning environments

TL;DR

This paper reviews various indicators beyond correctness, like motivation and emotions, to improve adaptive learning in virtual environments, aiming for more comprehensive student assessment.

Contribution

It systematically reviews diverse learning indicators beyond correctness, proposing a broader approach for adaptive learning in virtual environments.

Findings

Motivation and emotions influence learning outcomes.

Physiological and brain imaging data can inform adaptive strategies.

Prior knowledge is crucial for personalized learning.

Abstract

Student learning development must involve more than just correcting or incorrect questions. However, most adaptive learning methods in Virtual Learning Environments are based on whether the student's response is incorrect or correct. This perspective is limited in assessing the student's learning level, as it does not consider other elements that can be crucial in this process. The objective of this work is to conduct a Systematic Literature Review (SLR) to elucidate which learning indicators influence student learning and which can be implemented in a VLE to assist in adaptive learning. The works selected and filtered by qualitative assessment reveal a comprehensive approach to assessing different aspects of the learning in virtual environments, such as motivation, emotions, physiological responses, brain imaging, and the students' prior knowledge. The discussion of these new indicators allows adaptive technology developers to implement more appropriate solutions to students' realities, resulting in more complete training.