From Clicks to Constructs: An Examination of Validity Evidence of Game-Based Indicators Derived From Theory

• In Event: Assessing Student Learning From a Cognitive Perspective: Challenges and Innovations

Abstract

This study aims to examine preliminary validity evidence on various game-based indicators (GBI) from a variety of games, where the indicators represent complex learning processes or strategies. An essential feature of this work is that all GBIs were developed from a theoretical framework and not from unsupervised feature extraction methods (i.e., machine learning). Three examples of theory-based GBI are provided and validity evidence presented. Successful algorithm development requires understanding the underlying theory, how the theory is instantiated under different game conditions, and programming that can take into account these exigencies using fine-grained gameplay data.

Authors

• Tianying Feng, National Center for Research on Evaluation, Standards, and Student Testing

• Gregory K.W.K. Chung, University of California - Los Angeles