Transparent Player Model: Adaptive Visualization of Learner Model in Educational Games

Abstract

Despite the success of Learning Analytics (LA), there are two obstacles to its application in educational games, including transparency in assessing educational outcomes in real-time gameplay, and clarity in representing those results to players. Open learner model (OLM) is a valuable instrument with capability to improve learning that meets such challenges. However, OLMs usually suffer issues concerning interactivity and transparency, which mostly regard the assessment mechanism that is used to evaluate learners’ knowledge. Tackling down transparency issues would offer context for interpreting and comparing learner model information, as well as promoting interactivity. As there is lack of studies investigating the potential of OLMs in educational games, we argue that this work can provide a valuable starting point for applying OLMs or adaptive visualizations of players’ learner models within gameplay sessions, which, in turn, can help to address both issues of application of LA to game research and OLMs. As a case study, we introduce the proposed approach into our adaptive computational thinking game.