Personalization in OELEs: Developing a Data-Driven Framework to Model and Scaffold SRL Processes

Abstract

This research focuses on developing a data-driven framework for modeling and scaffolding learners’ self-regulated learning (SRL) processes in open-ended learning environments (OELE). The aim of this work is to offer a personalized and productive learning experience by adapting scaffolds to help learners develop self-regulation skills and strategies. This research applies mining techniques on data collected from multiple channels to track learners’ cognitive, affective, metacognitive and motivational (CAMM) processes as they work in Betty’s Brain, a computer-based OELE. The CAMM information is used to derive online models of learners’ SRL processes. These learner models inform the design of personalized scaffolds that help students develop the required SRL process and become more proficient learners. The significance of this research lies in developing and using data-driven learner SRL models to personalize and contextualize the scaffolds provided to learners within the OELE.